ppo-Pyramids / run_logs /timers.json
user87441257's picture
First Push
99b1a23 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3861065208911896,
"min": 0.3861065208911896,
"max": 1.5357246398925781,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11607.90625,
"min": 11607.90625,
"max": 46587.7421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989897.0,
"min": 29952.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989897.0,
"min": 29952.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5410311818122864,
"min": -0.10919022560119629,
"max": 0.5998331308364868,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 148.7835693359375,
"min": -26.424034118652344,
"max": 170.3526153564453,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.010859187692403793,
"min": -0.020631836727261543,
"max": 0.3483094871044159,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -2.986276626586914,
"min": -5.529332160949707,
"max": 82.54934692382812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0683969497400713,
"min": 0.06435283409781803,
"max": 0.07397746552777,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9575572963609982,
"min": 0.5027168508168797,
"max": 1.0594629125598836,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016890029016871096,
"min": 0.00035294050762710614,
"max": 0.016890029016871096,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23646040623619533,
"min": 0.0041317737671585095,
"max": 0.23646040623619533,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.681233153907142e-06,
"min": 7.681233153907142e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001075372641547,
"min": 0.0001075372641547,
"max": 0.0035082020305993995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256037857142859,
"min": 0.10256037857142859,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358453000000002,
"min": 1.3886848,
"max": 2.5728611,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026578181928571434,
"min": 0.00026578181928571434,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003720945470000001,
"min": 0.003720945470000001,
"max": 0.11696311993999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009575403295457363,
"min": 0.00936022400856018,
"max": 0.31407761573791504,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13405564427375793,
"min": 0.13104313611984253,
"max": 2.1985433101654053,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 320.258064516129,
"min": 318.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29784.0,
"min": 15984.0,
"max": 33987.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6086701892633388,
"min": -1.0000000521540642,
"max": 1.6422515279546226,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 151.21499779075384,
"min": -30.3952017724514,
"max": 159.2983982115984,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6086701892633388,
"min": -1.0000000521540642,
"max": 1.6422515279546226,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 151.21499779075384,
"min": -30.3952017724514,
"max": 159.2983982115984,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03192848589505376,
"min": 0.03192848589505376,
"max": 5.831131956540048,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.0012776741350535,
"min": 2.6949346217443235,
"max": 93.29811130464077,
"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": "1719747201",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1719749405"
},
"total": 2204.2946563220003,
"count": 1,
"self": 0.49051521900037187,
"children": {
"run_training.setup": {
"total": 0.05919794700002967,
"count": 1,
"self": 0.05919794700002967
},
"TrainerController.start_learning": {
"total": 2203.744943156,
"count": 1,
"self": 1.3956978180417536,
"children": {
"TrainerController._reset_env": {
"total": 3.392763477000017,
"count": 1,
"self": 3.392763477000017
},
"TrainerController.advance": {
"total": 2198.869358519958,
"count": 63875,
"self": 1.4409579338966978,
"children": {
"env_step": {
"total": 1559.2695782960595,
"count": 63875,
"self": 1421.9226601850282,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.4718943150159,
"count": 63875,
"self": 4.852315856999212,
"children": {
"TorchPolicy.evaluate": {
"total": 131.6195784580167,
"count": 62555,
"self": 131.6195784580167
}
}
},
"workers": {
"total": 0.8750237960152845,
"count": 63875,
"self": 0.0,
"children": {
"worker_root": {
"total": 2198.401708715036,
"count": 63875,
"is_parallel": true,
"self": 900.3875292310786,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006727416999979141,
"count": 1,
"is_parallel": true,
"self": 0.005227386000115075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001500030999864066,
"count": 8,
"is_parallel": true,
"self": 0.001500030999864066
}
}
},
"UnityEnvironment.step": {
"total": 0.08351494599992293,
"count": 1,
"is_parallel": true,
"self": 0.0006839659998831848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005004040000358145,
"count": 1,
"is_parallel": true,
"self": 0.0005004040000358145
},
"communicator.exchange": {
"total": 0.08038778100001309,
"count": 1,
"is_parallel": true,
"self": 0.08038778100001309
},
"steps_from_proto": {
"total": 0.0019427949999908378,
"count": 1,
"is_parallel": true,
"self": 0.0004166070001474509,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001526187999843387,
"count": 8,
"is_parallel": true,
"self": 0.001526187999843387
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1298.0141794839574,
"count": 63874,
"is_parallel": true,
"self": 34.42356120697559,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.139877045999583,
"count": 63874,
"is_parallel": true,
"self": 24.139877045999583
},
"communicator.exchange": {
"total": 1138.754403594955,
"count": 63874,
"is_parallel": true,
"self": 1138.754403594955
},
"steps_from_proto": {
"total": 100.69633763602712,
"count": 63874,
"is_parallel": true,
"self": 20.779066134029335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.91727150199779,
"count": 510992,
"is_parallel": true,
"self": 79.91727150199779
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 638.1588222900017,
"count": 63875,
"self": 2.6730239959891833,
"children": {
"process_trajectory": {
"total": 130.936165789013,
"count": 63875,
"self": 130.5935656830128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.34260010600019086,
"count": 2,
"self": 0.34260010600019086
}
}
},
"_update_policy": {
"total": 504.5496325049995,
"count": 451,
"self": 298.1384779639668,
"children": {
"TorchPPOOptimizer.update": {
"total": 206.41115454103272,
"count": 22812,
"self": 206.41115454103272
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0320000001229346e-06,
"count": 1,
"self": 1.0320000001229346e-06
},
"TrainerController._save_models": {
"total": 0.08712230900027862,
"count": 1,
"self": 0.0013811490002808569,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08574115999999776,
"count": 1,
"self": 0.08574115999999776
}
}
}
}
}
}
}