Pyramids_Ver1 / run_logs /timers.json
Varaprabha's picture
Done
639e674
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1253465861082077,
"min": 0.1252432018518448,
"max": 1.5088448524475098,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3780.453125,
"min": 3763.3076171875,
"max": 45772.31640625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999923.0,
"min": 29952.0,
"max": 2999923.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999923.0,
"min": 29952.0,
"max": 2999923.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8327298164367676,
"min": -0.1594657450914383,
"max": 0.8889648914337158,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 248.98622131347656,
"min": -37.79338073730469,
"max": 275.5356140136719,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0006672461167909205,
"min": -0.006117664743214846,
"max": 0.22224584221839905,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.19950659573078156,
"min": -1.8352994918823242,
"max": 52.672264099121094,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06696398693851993,
"min": 0.06318595896231101,
"max": 0.07407946747151159,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9374958171392791,
"min": 0.48312098479323917,
"max": 1.0903383475835617,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01453593165829911,
"min": 0.00038570372701885553,
"max": 0.017996893948171007,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20350304321618753,
"min": 0.0053998521782639775,
"max": 0.2519565152743941,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5752066178214294e-06,
"min": 1.5752066178214294e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.205289264950001e-05,
"min": 2.205289264950001e-05,
"max": 0.0039693408768863995,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10052503571428573,
"min": 0.10052503571428573,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4073505000000002,
"min": 1.3962282666666668,
"max": 2.7825895999999997,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.24510678571429e-05,
"min": 6.24510678571429e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008743149500000005,
"min": 0.0008743149500000005,
"max": 0.13231904864000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007707708980888128,
"min": 0.007707708980888128,
"max": 0.37930193543434143,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10790792852640152,
"min": 0.10790792852640152,
"max": 2.655113458633423,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 196.38709677419354,
"min": 196.38709677419354,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30440.0,
"min": 15984.0,
"max": 33980.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.8030649242656571,
"min": -1.0000000521540642,
"max": 1.8030649242656571,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 277.6719983369112,
"min": -29.185601733624935,
"max": 277.6719983369112,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.8030649242656571,
"min": -1.0000000521540642,
"max": 1.8030649242656571,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 277.6719983369112,
"min": -29.185601733624935,
"max": 277.6719983369112,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01578316032497572,
"min": 0.01578316032497572,
"max": 7.56246564630419,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.430606690046261,
"min": 2.2691826149675762,
"max": 120.99945034086704,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1686203145",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1686210633"
},
"total": 7488.187534739,
"count": 1,
"self": 0.4898379220003335,
"children": {
"run_training.setup": {
"total": 0.053705555000078675,
"count": 1,
"self": 0.053705555000078675
},
"TrainerController.start_learning": {
"total": 7487.643991261999,
"count": 1,
"self": 4.560899504193003,
"children": {
"TrainerController._reset_env": {
"total": 4.964794415000142,
"count": 1,
"self": 4.964794415000142
},
"TrainerController.advance": {
"total": 7478.020075878805,
"count": 195356,
"self": 4.5513074251466605,
"children": {
"env_step": {
"total": 5551.3292674248905,
"count": 195356,
"self": 5208.510174080397,
"children": {
"SubprocessEnvManager._take_step": {
"total": 340.16061003317964,
"count": 195356,
"self": 15.226159354986748,
"children": {
"TorchPolicy.evaluate": {
"total": 324.9344506781929,
"count": 187571,
"self": 324.9344506781929
}
}
},
"workers": {
"total": 2.6584833113145123,
"count": 195356,
"self": 0.0,
"children": {
"worker_root": {
"total": 7470.428837384021,
"count": 195356,
"is_parallel": true,
"self": 2628.8191961470366,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028036300000167103,
"count": 1,
"is_parallel": true,
"self": 0.0007287140003882087,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020749159996285016,
"count": 8,
"is_parallel": true,
"self": 0.0020749159996285016
}
}
},
"UnityEnvironment.step": {
"total": 0.05964577700001428,
"count": 1,
"is_parallel": true,
"self": 0.0006089030000566709,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005271699999411794,
"count": 1,
"is_parallel": true,
"self": 0.0005271699999411794
},
"communicator.exchange": {
"total": 0.05641422799999418,
"count": 1,
"is_parallel": true,
"self": 0.05641422799999418
},
"steps_from_proto": {
"total": 0.002095476000022245,
"count": 1,
"is_parallel": true,
"self": 0.00046528600023520994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001630189999787035,
"count": 8,
"is_parallel": true,
"self": 0.001630189999787035
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4841.609641236984,
"count": 195355,
"is_parallel": true,
"self": 102.30292759051281,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 72.89769139374084,
"count": 195355,
"is_parallel": true,
"self": 72.89769139374084
},
"communicator.exchange": {
"total": 4339.127580643964,
"count": 195355,
"is_parallel": true,
"self": 4339.127580643964
},
"steps_from_proto": {
"total": 327.28144160876695,
"count": 195355,
"is_parallel": true,
"self": 67.05534227468252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 260.22609933408444,
"count": 1562840,
"is_parallel": true,
"self": 260.22609933408444
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1922.1395010287677,
"count": 195356,
"self": 8.709603228714286,
"children": {
"process_trajectory": {
"total": 349.71141674602677,
"count": 195356,
"self": 348.97878334002735,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7326334059994224,
"count": 6,
"self": 0.7326334059994224
}
}
},
"_update_policy": {
"total": 1563.7184810540266,
"count": 1400,
"self": 1004.1124203512111,
"children": {
"TorchPPOOptimizer.update": {
"total": 559.6060607028155,
"count": 68376,
"self": 559.6060607028155
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2180007615825161e-06,
"count": 1,
"self": 1.2180007615825161e-06
},
"TrainerController._save_models": {
"total": 0.09822024599998258,
"count": 1,
"self": 0.0013573779997386737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0968628680002439,
"count": 1,
"self": 0.0968628680002439
}
}
}
}
}
}
}