ppo-Pyramids / run_logs /timers.json
cfisicaro's picture
First training of Pyramids
16471e7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4569108188152313,
"min": 0.4386003613471985,
"max": 1.4935568571090698,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13656.150390625,
"min": 13143.9755859375,
"max": 45308.5390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989993.0,
"min": 29925.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989993.0,
"min": 29925.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.416199654340744,
"min": -0.10980607569217682,
"max": 0.4318245053291321,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 111.54150390625,
"min": -26.353458404541016,
"max": 115.2971420288086,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.04461498185992241,
"min": -0.020444901660084724,
"max": 0.21282711625099182,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 11.956814765930176,
"min": -5.397454261779785,
"max": 51.07850646972656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06904298685999709,
"min": 0.06615706136896429,
"max": 0.07330365463599452,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9666018160399593,
"min": 0.5131255824519616,
"max": 1.0462562727531322,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01640664887132256,
"min": 0.0003229313506031613,
"max": 0.01640664887132256,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22969308419851583,
"min": 0.0029063821554284517,
"max": 0.22969308419851583,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.741833133707142e-06,
"min": 7.741833133707142e-06,
"max": 0.0002952340730172143,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001083856638719,
"min": 0.0001083856638719,
"max": 0.0032597834134055997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258057857142858,
"min": 0.10258057857142858,
"max": 0.19841135714285715,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361281000000001,
"min": 1.3888795,
"max": 2.3865944,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026779979928571426,
"min": 0.00026779979928571426,
"max": 0.009841294578571427,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00374919719,
"min": 0.00374919719,
"max": 0.10868078056,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011930093169212341,
"min": 0.011930093169212341,
"max": 0.3458973467350006,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16702130436897278,
"min": 0.16702130436897278,
"max": 2.421281337738037,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 418.15942028985506,
"min": 409.97333333333336,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28853.0,
"min": 16724.0,
"max": 33428.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4012735124458284,
"min": -0.9999806972280625,
"max": 1.5121969021283663,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 95.28659884631634,
"min": -31.998801663517952,
"max": 107.25059796869755,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4012735124458284,
"min": -0.9999806972280625,
"max": 1.5121969021283663,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 95.28659884631634,
"min": -31.998801663517952,
"max": 107.25059796869755,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05168019612606526,
"min": 0.05123724499872575,
"max": 6.504010521313724,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.5142533365724375,
"min": 3.5142533365724375,
"max": 110.5681788623333,
"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": "1676282557",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676286200"
},
"total": 3643.354544879,
"count": 1,
"self": 0.7382884999997259,
"children": {
"run_training.setup": {
"total": 0.13920456699997885,
"count": 1,
"self": 0.13920456699997885
},
"TrainerController.start_learning": {
"total": 3642.4770518120004,
"count": 1,
"self": 2.292935639915413,
"children": {
"TrainerController._reset_env": {
"total": 5.199905201999854,
"count": 1,
"self": 5.199905201999854
},
"TrainerController.advance": {
"total": 3634.8772996850853,
"count": 63562,
"self": 2.474626102072307,
"children": {
"env_step": {
"total": 2379.0509493529544,
"count": 63562,
"self": 2229.96194124097,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.63381605198174,
"count": 63562,
"self": 7.210155286046529,
"children": {
"TorchPolicy.evaluate": {
"total": 140.4236607659352,
"count": 62568,
"self": 29.903896544856252,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.51976422107896,
"count": 62568,
"self": 110.51976422107896
}
}
}
}
},
"workers": {
"total": 1.4551920600026733,
"count": 63562,
"self": 0.0,
"children": {
"worker_root": {
"total": 3635.3612441210694,
"count": 63562,
"is_parallel": true,
"self": 1583.901092488059,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029610030001094856,
"count": 1,
"is_parallel": true,
"self": 0.0011789800000769901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017820230000324955,
"count": 8,
"is_parallel": true,
"self": 0.0017820230000324955
}
}
},
"UnityEnvironment.step": {
"total": 0.11455973500005712,
"count": 1,
"is_parallel": true,
"self": 0.0006661169998096739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005255060000308731,
"count": 1,
"is_parallel": true,
"self": 0.0005255060000308731
},
"communicator.exchange": {
"total": 0.11020975400015232,
"count": 1,
"is_parallel": true,
"self": 0.11020975400015232
},
"steps_from_proto": {
"total": 0.003158358000064254,
"count": 1,
"is_parallel": true,
"self": 0.0005258199998934288,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026325380001708254,
"count": 8,
"is_parallel": true,
"self": 0.0026325380001708254
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2051.4601516330104,
"count": 63561,
"is_parallel": true,
"self": 45.893988772239254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.52401530799375,
"count": 63561,
"is_parallel": true,
"self": 27.52401530799375
},
"communicator.exchange": {
"total": 1830.8269467408336,
"count": 63561,
"is_parallel": true,
"self": 1830.8269467408336
},
"steps_from_proto": {
"total": 147.21520081194376,
"count": 63561,
"is_parallel": true,
"self": 34.60878311273132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 112.60641769921244,
"count": 508488,
"is_parallel": true,
"self": 112.60641769921244
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1253.3517242300588,
"count": 63562,
"self": 4.535835709046978,
"children": {
"process_trajectory": {
"total": 228.7104991820072,
"count": 63562,
"self": 228.47072937300732,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2397698089998812,
"count": 2,
"self": 0.2397698089998812
}
}
},
"_update_policy": {
"total": 1020.1053893390047,
"count": 441,
"self": 265.67095314998255,
"children": {
"TorchPPOOptimizer.update": {
"total": 754.4344361890221,
"count": 22797,
"self": 754.4344361890221
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0890007615671493e-06,
"count": 1,
"self": 1.0890007615671493e-06
},
"TrainerController._save_models": {
"total": 0.10691019599926221,
"count": 1,
"self": 0.0036140659985903767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10329613000067184,
"count": 1,
"self": 0.10329613000067184
}
}
}
}
}
}
}