ppo-Pyramids / run_logs /timers.json
droid22's picture
First Push
4b6354c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.557577908039093,
"min": 0.5487788915634155,
"max": 1.4842499494552612,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16736.2578125,
"min": 16445.806640625,
"max": 45026.20703125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989977.0,
"min": 29952.0,
"max": 989977.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989977.0,
"min": 29952.0,
"max": 989977.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4270130395889282,
"min": -0.15093789994716644,
"max": 0.4956008195877075,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 115.72053527832031,
"min": -35.772281646728516,
"max": 135.2990264892578,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009312311187386513,
"min": -0.00689808651804924,
"max": 0.28118979930877686,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.5236363410949707,
"min": -1.8094918727874756,
"max": 66.64198303222656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0655950898788341,
"min": 0.0655950898788341,
"max": 0.07344480949896158,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9183312583036775,
"min": 0.514113666492731,
"max": 1.0792990173761021,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012956875807580249,
"min": 0.00012337469975598562,
"max": 0.014335634103017152,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1813962613061235,
"min": 0.0017272457965837986,
"max": 0.20069887744224013,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.48957607493571e-06,
"min": 7.48957607493571e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010485406504909995,
"min": 0.00010485406504909995,
"max": 0.003634428788523799,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249649285714287,
"min": 0.10249649285714287,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349509,
"min": 1.3886848,
"max": 2.6114762,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025939963642857136,
"min": 0.00025939963642857136,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036315949099999987,
"min": 0.0036315949099999987,
"max": 0.12116647237999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006474309600889683,
"min": 0.006474309600889683,
"max": 0.3778093755245209,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09064033627510071,
"min": 0.09064033627510071,
"max": 2.6446657180786133,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 432.1304347826087,
"min": 375.7236842105263,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29817.0,
"min": 15984.0,
"max": 32254.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.393898524235988,
"min": -1.0000000521540642,
"max": 1.5453052516830594,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 96.17899817228317,
"min": -31.994401663541794,
"max": 118.23859833180904,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.393898524235988,
"min": -1.0000000521540642,
"max": 1.5453052516830594,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 96.17899817228317,
"min": -31.994401663541794,
"max": 118.23859833180904,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.029060049179795475,
"min": 0.029060049179795475,
"max": 7.597675563767552,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.0051433934058878,
"min": 2.0051433934058878,
"max": 121.56280902028084,
"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": "1679757806",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679759944"
},
"total": 2138.218557879,
"count": 1,
"self": 0.48214502699966033,
"children": {
"run_training.setup": {
"total": 0.1095355049999398,
"count": 1,
"self": 0.1095355049999398
},
"TrainerController.start_learning": {
"total": 2137.626877347,
"count": 1,
"self": 1.3473574700128665,
"children": {
"TrainerController._reset_env": {
"total": 6.055290014000093,
"count": 1,
"self": 6.055290014000093
},
"TrainerController.advance": {
"total": 2130.130055183987,
"count": 63620,
"self": 1.4341828739966331,
"children": {
"env_step": {
"total": 1500.11583490305,
"count": 63620,
"self": 1390.589853777066,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.70265528002142,
"count": 63620,
"self": 4.674476889029393,
"children": {
"TorchPolicy.evaluate": {
"total": 104.02817839099203,
"count": 62558,
"self": 104.02817839099203
}
}
},
"workers": {
"total": 0.8233258459624722,
"count": 63620,
"self": 0.0,
"children": {
"worker_root": {
"total": 2133.090198903019,
"count": 63620,
"is_parallel": true,
"self": 857.6514887390704,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018502640000406245,
"count": 1,
"is_parallel": true,
"self": 0.0005942679999861866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001255996000054438,
"count": 8,
"is_parallel": true,
"self": 0.001255996000054438
}
}
},
"UnityEnvironment.step": {
"total": 0.04832894099990881,
"count": 1,
"is_parallel": true,
"self": 0.0005586169997968682,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005171820000668959,
"count": 1,
"is_parallel": true,
"self": 0.0005171820000668959
},
"communicator.exchange": {
"total": 0.04561982400014131,
"count": 1,
"is_parallel": true,
"self": 0.04561982400014131
},
"steps_from_proto": {
"total": 0.0016333179999037384,
"count": 1,
"is_parallel": true,
"self": 0.00036409100016498996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012692269997387484,
"count": 8,
"is_parallel": true,
"self": 0.0012692269997387484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.4387101639486,
"count": 63619,
"is_parallel": true,
"self": 31.447785261013905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.935696252945036,
"count": 63619,
"is_parallel": true,
"self": 22.935696252945036
},
"communicator.exchange": {
"total": 1128.7558930469763,
"count": 63619,
"is_parallel": true,
"self": 1128.7558930469763
},
"steps_from_proto": {
"total": 92.29933560301333,
"count": 63619,
"is_parallel": true,
"self": 19.528584464103233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.7707511389101,
"count": 508952,
"is_parallel": true,
"self": 72.7707511389101
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 628.5800374069406,
"count": 63620,
"self": 2.54572609789966,
"children": {
"process_trajectory": {
"total": 116.4714101410359,
"count": 63620,
"self": 116.26858930203662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20282083899928693,
"count": 2,
"self": 0.20282083899928693
}
}
},
"_update_policy": {
"total": 509.56290116800506,
"count": 453,
"self": 323.71691810498237,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.8459830630227,
"count": 22806,
"self": 185.8459830630227
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2149998838140164e-06,
"count": 1,
"self": 1.2149998838140164e-06
},
"TrainerController._save_models": {
"total": 0.09417346400005044,
"count": 1,
"self": 0.0015297570002985594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09264370699975188,
"count": 1,
"self": 0.09264370699975188
}
}
}
}
}
}
}