cgwell's picture
First Push
8586ac5 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.44394034147262573,
"min": 0.44394034147262573,
"max": 1.4034472703933716,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13367.931640625,
"min": 13367.931640625,
"max": 42574.9765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989946.0,
"min": 29952.0,
"max": 989946.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5386329293251038,
"min": -0.1231832206249237,
"max": 0.6282528638839722,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 150.27859497070312,
"min": -29.687156677246094,
"max": 176.5390625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03880328685045242,
"min": -0.03321768715977669,
"max": 0.3464418649673462,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.826116561889648,
"min": -8.968775749206543,
"max": 83.49249267578125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06571567507414408,
"min": 0.06442848470766996,
"max": 0.07315681449145633,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9200194510380172,
"min": 0.5022719418691891,
"max": 1.048381804313976,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014447298315257494,
"min": 0.00039720566548459086,
"max": 0.015270755481088557,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20226217641360492,
"min": 0.005475509034927284,
"max": 0.22537571884002353,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.51235463877143e-06,
"min": 7.51235463877143e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010517296494280001,
"min": 0.00010517296494280001,
"max": 0.0033763324745558995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250408571428572,
"min": 0.10250408571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4350572000000001,
"min": 1.3886848,
"max": 2.4853192,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002601581628571429,
"min": 0.0002601581628571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036422142800000006,
"min": 0.0036422142800000006,
"max": 0.11256186559,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.015890296548604965,
"min": 0.015746204182505608,
"max": 0.5124168992042542,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2224641591310501,
"min": 0.2204468548297882,
"max": 3.5869181156158447,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 344.1034482758621,
"min": 310.1326530612245,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29937.0,
"min": 15984.0,
"max": 33461.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5422340719537302,
"min": -1.0000000521540642,
"max": 1.6286224344251108,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 135.71659833192825,
"min": -29.918001614511013,
"max": 159.60499857366085,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5422340719537302,
"min": -1.0000000521540642,
"max": 1.6286224344251108,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 135.71659833192825,
"min": -29.918001614511013,
"max": 159.60499857366085,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.056210733514738175,
"min": 0.05124698104295281,
"max": 10.209204433485866,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.946544549296959,
"min": 4.728752595066908,
"max": 163.34727093577385,
"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": "1720826538",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "1720829788"
},
"total": 3250.5263523410003,
"count": 1,
"self": 1.5730113810000148,
"children": {
"run_training.setup": {
"total": 0.07200584700012769,
"count": 1,
"self": 0.07200584700012769
},
"TrainerController.start_learning": {
"total": 3248.881335113,
"count": 1,
"self": 2.3146919960026935,
"children": {
"TrainerController._reset_env": {
"total": 3.052876551000054,
"count": 1,
"self": 3.052876551000054
},
"TrainerController.advance": {
"total": 3243.3844977009962,
"count": 63768,
"self": 2.6494927059898146,
"children": {
"env_step": {
"total": 2168.0295542660388,
"count": 63768,
"self": 2006.866629247862,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.7368428730747,
"count": 63768,
"self": 7.030014184035053,
"children": {
"TorchPolicy.evaluate": {
"total": 152.70682868903964,
"count": 62560,
"self": 152.70682868903964
}
}
},
"workers": {
"total": 1.4260821451021002,
"count": 63768,
"self": 0.0,
"children": {
"worker_root": {
"total": 3241.229304512014,
"count": 63768,
"is_parallel": true,
"self": 1420.9973553440072,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0032341129999622353,
"count": 1,
"is_parallel": true,
"self": 0.0010619749998568295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002172138000105406,
"count": 8,
"is_parallel": true,
"self": 0.002172138000105406
}
}
},
"UnityEnvironment.step": {
"total": 0.07012525899995126,
"count": 1,
"is_parallel": true,
"self": 0.0007817499999873689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005387920000430313,
"count": 1,
"is_parallel": true,
"self": 0.0005387920000430313
},
"communicator.exchange": {
"total": 0.06661467499998253,
"count": 1,
"is_parallel": true,
"self": 0.06661467499998253
},
"steps_from_proto": {
"total": 0.0021900419999383303,
"count": 1,
"is_parallel": true,
"self": 0.00045202499973129306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017380170002070372,
"count": 8,
"is_parallel": true,
"self": 0.0017380170002070372
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1820.2319491680068,
"count": 63767,
"is_parallel": true,
"self": 50.71265846896472,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.13721208802008,
"count": 63767,
"is_parallel": true,
"self": 31.13721208802008
},
"communicator.exchange": {
"total": 1608.890883777966,
"count": 63767,
"is_parallel": true,
"self": 1608.890883777966
},
"steps_from_proto": {
"total": 129.49119483305594,
"count": 63767,
"is_parallel": true,
"self": 28.220081013930894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 101.27111381912505,
"count": 510136,
"is_parallel": true,
"self": 101.27111381912505
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1072.7054507289674,
"count": 63768,
"self": 4.612326001012207,
"children": {
"process_trajectory": {
"total": 164.25154220795025,
"count": 63768,
"self": 163.99451474295097,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25702746499928253,
"count": 2,
"self": 0.25702746499928253
}
}
},
"_update_policy": {
"total": 903.841582520005,
"count": 450,
"self": 373.32190645799756,
"children": {
"TorchPPOOptimizer.update": {
"total": 530.5196760620074,
"count": 22821,
"self": 530.5196760620074
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4510005712509155e-06,
"count": 1,
"self": 1.4510005712509155e-06
},
"TrainerController._save_models": {
"total": 0.12926741400042374,
"count": 1,
"self": 0.0029133730013199965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12635404099910374,
"count": 1,
"self": 0.12635404099910374
}
}
}
}
}
}
}