pyramids / run_logs /timers.json
sugarblock's picture
first training of Pyramids
7a01e73 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.37877386808395386,
"min": 0.3725875914096832,
"max": 1.3768521547317505,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11490.484375,
"min": 11088.20703125,
"max": 41768.1875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989976.0,
"min": 29952.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989976.0,
"min": 29952.0,
"max": 989976.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.61464923620224,
"min": -0.10584463179111481,
"max": 0.6207893490791321,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 175.17503356933594,
"min": -25.508556365966797,
"max": 175.17503356933594,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.027042478322982788,
"min": -0.01966295950114727,
"max": 0.540077805519104,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.707106113433838,
"min": -5.308999061584473,
"max": 127.9984359741211,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07049412893095343,
"min": 0.06436603157466383,
"max": 0.07449891368259223,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9869178050333479,
"min": 0.5042451982641989,
"max": 1.0477014859401002,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01855766706215772,
"min": 0.00048281804636293805,
"max": 0.01855766706215772,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.25980733887020807,
"min": 0.005793816556355256,
"max": 0.25980733887020807,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.446354660771429e-06,
"min": 7.446354660771429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001042489652508,
"min": 0.0001042489652508,
"max": 0.0033745768751410996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248208571428573,
"min": 0.10248208571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4347492000000002,
"min": 1.3886848,
"max": 2.4434784000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002579603628571429,
"min": 0.0002579603628571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00361144508,
"min": 0.00361144508,
"max": 0.11250340411000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012783450074493885,
"min": 0.012783450074493885,
"max": 0.7644051313400269,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17896829545497894,
"min": 0.17896829545497894,
"max": 5.350835800170898,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 284.12264150943395,
"min": 284.12264150943395,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30117.0,
"min": 15984.0,
"max": 33399.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7168784906095433,
"min": -1.0000000521540642,
"max": 1.7168784906095433,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 183.70599849522114,
"min": -30.999001637101173,
"max": 183.70599849522114,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7168784906095433,
"min": -1.0000000521540642,
"max": 1.7168784906095433,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 183.70599849522114,
"min": -30.999001637101173,
"max": 183.70599849522114,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03780564956941476,
"min": 0.03780564956941476,
"max": 15.011044334620237,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.04520450392738,
"min": 3.975228239840362,
"max": 240.1767093539238,
"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": "1738412208",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/sugarblock/miniconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --force --no-graphics",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1738413615"
},
"total": 1526.1702171630004,
"count": 1,
"self": 0.32336627599943313,
"children": {
"run_training.setup": {
"total": 0.007270825000887271,
"count": 1,
"self": 0.007270825000887271
},
"TrainerController.start_learning": {
"total": 1525.839580062,
"count": 1,
"self": 0.6699915929730196,
"children": {
"TrainerController._reset_env": {
"total": 2.7815671020016453,
"count": 1,
"self": 2.7815671020016453
},
"TrainerController.advance": {
"total": 1522.347144539026,
"count": 63977,
"self": 0.603698602064469,
"children": {
"env_step": {
"total": 938.4579598680521,
"count": 63977,
"self": 762.0294922010635,
"children": {
"SubprocessEnvManager._take_step": {
"total": 176.01812953319313,
"count": 63977,
"self": 2.062060184456641,
"children": {
"TorchPolicy.evaluate": {
"total": 173.9560693487365,
"count": 62564,
"self": 173.9560693487365
}
}
},
"workers": {
"total": 0.4103381337954488,
"count": 63977,
"self": 0.0,
"children": {
"worker_root": {
"total": 1523.606262621779,
"count": 63977,
"is_parallel": true,
"self": 807.4014099187261,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001852595998570905,
"count": 1,
"is_parallel": true,
"self": 0.0009810930023377296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008715029962331755,
"count": 8,
"is_parallel": true,
"self": 0.0008715029962331755
}
}
},
"UnityEnvironment.step": {
"total": 0.018162405000111903,
"count": 1,
"is_parallel": true,
"self": 0.000146419999509817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015986700054781977,
"count": 1,
"is_parallel": true,
"self": 0.00015986700054781977
},
"communicator.exchange": {
"total": 0.017384049000611412,
"count": 1,
"is_parallel": true,
"self": 0.017384049000611412
},
"steps_from_proto": {
"total": 0.00047206899944285396,
"count": 1,
"is_parallel": true,
"self": 0.00011589699897740502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00035617200046544895,
"count": 8,
"is_parallel": true,
"self": 0.00035617200046544895
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 716.2048527030529,
"count": 63976,
"is_parallel": true,
"self": 7.826616480500888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.55806151264369,
"count": 63976,
"is_parallel": true,
"self": 5.55806151264369
},
"communicator.exchange": {
"total": 680.6077958471215,
"count": 63976,
"is_parallel": true,
"self": 680.6077958471215
},
"steps_from_proto": {
"total": 22.212378862786863,
"count": 63976,
"is_parallel": true,
"self": 5.097733844850154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.11464501793671,
"count": 511808,
"is_parallel": true,
"self": 17.11464501793671
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 583.2854860689094,
"count": 63977,
"self": 1.3299228132564167,
"children": {
"process_trajectory": {
"total": 76.89881136867189,
"count": 63977,
"self": 76.76340873267327,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13540263599861646,
"count": 2,
"self": 0.13540263599861646
}
}
},
"_update_policy": {
"total": 505.05675188698115,
"count": 449,
"self": 178.12567785401006,
"children": {
"TorchPPOOptimizer.update": {
"total": 326.9310740329711,
"count": 22809,
"self": 326.9310740329711
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.78999344422482e-07,
"count": 1,
"self": 8.78999344422482e-07
},
"TrainerController._save_models": {
"total": 0.04087594900011027,
"count": 1,
"self": 0.0007693040006415686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0401066449994687,
"count": 1,
"self": 0.0401066449994687
}
}
}
}
}
}
}