Pyramids / run_logs /timers.json
JeonHyoSeok's picture
First Push
5ffacb3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.256462961435318,
"min": 0.24931007623672485,
"max": 1.4535866975784302,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7722.61279296875,
"min": 7527.169921875,
"max": 44096.0078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989903.0,
"min": 29939.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989903.0,
"min": 29939.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5132403373718262,
"min": -0.10140679776668549,
"max": 0.620235025882721,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 139.088134765625,
"min": -24.337631225585938,
"max": 169.94439697265625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03418776020407677,
"min": 0.014041220769286156,
"max": 0.3614201247692108,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.264883041381836,
"min": 3.693223714828491,
"max": 85.65657043457031,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07033867048620084,
"min": 0.06391461724046604,
"max": 0.0748961377585325,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9847413868068117,
"min": 0.645295839187079,
"max": 1.1234420663779876,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014083578471374484,
"min": 0.0004239857394333098,
"max": 0.0162660280154191,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19717009859924278,
"min": 0.005935800352066338,
"max": 0.22772439221586738,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.437911806442858e-06,
"min": 7.437911806442858e-06,
"max": 0.0002948759017080333,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001041307652902,
"min": 0.0001041307652902,
"max": 0.0035076695307769004,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247927142857143,
"min": 0.10247927142857143,
"max": 0.19829196666666665,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4347098,
"min": 1.4347098,
"max": 2.5692230999999994,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002576792157142858,
"min": 0.0002576792157142858,
"max": 0.00982936747,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036075090200000013,
"min": 0.0036075090200000013,
"max": 0.11694538768999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011225721798837185,
"min": 0.011225721798837185,
"max": 0.4221051335334778,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15716010332107544,
"min": 0.15716010332107544,
"max": 3.7989461421966553,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 362.2597402597403,
"min": 305.375,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27894.0,
"min": 17505.0,
"max": 32517.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5338129638270899,
"min": -0.9999375520274043,
"max": 1.6912659414588136,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 118.10359821468592,
"min": -31.998001664876938,
"max": 158.9789984971285,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5338129638270899,
"min": -0.9999375520274043,
"max": 1.6912659414588136,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 118.10359821468592,
"min": -31.998001664876938,
"max": 158.9789984971285,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04159638291306479,
"min": 0.036821758271385494,
"max": 7.861568997303645,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.202921484305989,
"min": 3.202921484305989,
"max": 141.5082419514656,
"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": "1738560960",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738563169"
},
"total": 2209.0901614269997,
"count": 1,
"self": 0.5848942519992306,
"children": {
"run_training.setup": {
"total": 0.021566496000104962,
"count": 1,
"self": 0.021566496000104962
},
"TrainerController.start_learning": {
"total": 2208.4837006790003,
"count": 1,
"self": 1.3444561240225994,
"children": {
"TrainerController._reset_env": {
"total": 2.2432489100001476,
"count": 1,
"self": 2.2432489100001476
},
"TrainerController.advance": {
"total": 2204.750167357977,
"count": 63837,
"self": 1.3285823879687086,
"children": {
"env_step": {
"total": 1524.664032586138,
"count": 63837,
"self": 1373.9132925920353,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.96626898500836,
"count": 63837,
"self": 4.566436469967357,
"children": {
"TorchPolicy.evaluate": {
"total": 145.399832515041,
"count": 62562,
"self": 145.399832515041
}
}
},
"workers": {
"total": 0.7844710090944318,
"count": 63837,
"self": 0.0,
"children": {
"worker_root": {
"total": 2203.5111429179588,
"count": 63837,
"is_parallel": true,
"self": 939.5821918769752,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020681630003309692,
"count": 1,
"is_parallel": true,
"self": 0.0007035040002847381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001364659000046231,
"count": 8,
"is_parallel": true,
"self": 0.001364659000046231
}
}
},
"UnityEnvironment.step": {
"total": 0.06306558900041637,
"count": 1,
"is_parallel": true,
"self": 0.0005412250006884278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000617039000189834,
"count": 1,
"is_parallel": true,
"self": 0.000617039000189834
},
"communicator.exchange": {
"total": 0.06023840099987865,
"count": 1,
"is_parallel": true,
"self": 0.06023840099987865
},
"steps_from_proto": {
"total": 0.0016689239996594551,
"count": 1,
"is_parallel": true,
"self": 0.0003976149996560707,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012713090000033844,
"count": 8,
"is_parallel": true,
"self": 0.0012713090000033844
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.9289510409835,
"count": 63836,
"is_parallel": true,
"self": 30.80414181096512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.428958551986852,
"count": 63836,
"is_parallel": true,
"self": 22.428958551986852
},
"communicator.exchange": {
"total": 1118.717984788978,
"count": 63836,
"is_parallel": true,
"self": 1118.717984788978
},
"steps_from_proto": {
"total": 91.97786588905365,
"count": 63836,
"is_parallel": true,
"self": 18.0273519782495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.95051391080415,
"count": 510688,
"is_parallel": true,
"self": 73.95051391080415
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 678.75755238387,
"count": 63837,
"self": 2.594927620931685,
"children": {
"process_trajectory": {
"total": 126.65107951494201,
"count": 63837,
"self": 126.39664153294189,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2544379820001268,
"count": 2,
"self": 0.2544379820001268
}
}
},
"_update_policy": {
"total": 549.5115452479963,
"count": 457,
"self": 304.04399381501025,
"children": {
"TorchPPOOptimizer.update": {
"total": 245.46755143298606,
"count": 22818,
"self": 245.46755143298606
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8520004232414067e-06,
"count": 1,
"self": 1.8520004232414067e-06
},
"TrainerController._save_models": {
"total": 0.14582643500034465,
"count": 1,
"self": 0.002139207000254828,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14368722800008982,
"count": 1,
"self": 0.14368722800008982
}
}
}
}
}
}
}