ppo-Huggy / run_logs /timers.json
nadmozg's picture
Huggy
caae9e0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4098377227783203,
"min": 1.4098377227783203,
"max": 1.428949236869812,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68994.640625,
"min": 68994.640625,
"max": 77343.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.7140350877193,
"min": 81.80265339966833,
"max": 402.704,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49427.0,
"min": 49171.0,
"max": 50338.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49713.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49713.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3122682571411133,
"min": 0.13600899279117584,
"max": 2.473135471343994,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1317.992919921875,
"min": 16.865114212036133,
"max": 1450.1318359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5751917999041707,
"min": 1.843540349554631,
"max": 3.944327888926681,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2037.8593259453773,
"min": 228.59900334477425,
"max": 2290.172732591629,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5751917999041707,
"min": 1.843540349554631,
"max": 3.944327888926681,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2037.8593259453773,
"min": 228.59900334477425,
"max": 2290.172732591629,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014951848798490472,
"min": 0.01311035826705241,
"max": 0.018819996312352788,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.044855546395471416,
"min": 0.02622071653410482,
"max": 0.05357039508526213,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052848117136292984,
"min": 0.021742819963643946,
"max": 0.05889573320746422,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15854435140887896,
"min": 0.04348563992728789,
"max": 0.17036532287796338,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.222098926000003e-06,
"min": 3.222098926000003e-06,
"max": 0.00029534827655057494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.66629677800001e-06,
"min": 9.66629677800001e-06,
"max": 0.0008440929186356999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101074,
"min": 0.101074,
"max": 0.19844942499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303222,
"min": 0.20734035,
"max": 0.5813643,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.359260000000005e-05,
"min": 6.359260000000005e-05,
"max": 0.0049226263075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019077780000000016,
"min": 0.00019077780000000016,
"max": 0.01407007857,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699712804",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699715302"
},
"total": 2497.948187927,
"count": 1,
"self": 0.4365864070000498,
"children": {
"run_training.setup": {
"total": 0.053733005000026424,
"count": 1,
"self": 0.053733005000026424
},
"TrainerController.start_learning": {
"total": 2497.457868515,
"count": 1,
"self": 4.4947630831070455,
"children": {
"TrainerController._reset_env": {
"total": 8.813109879999956,
"count": 1,
"self": 8.813109879999956
},
"TrainerController.advance": {
"total": 2484.045910316893,
"count": 232481,
"self": 4.730828756052688,
"children": {
"env_step": {
"total": 1948.5432649087618,
"count": 232481,
"self": 1608.0618482758055,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.58936533593044,
"count": 232481,
"self": 17.374039365835415,
"children": {
"TorchPolicy.evaluate": {
"total": 320.215325970095,
"count": 222848,
"self": 320.215325970095
}
}
},
"workers": {
"total": 2.8920512970257732,
"count": 232481,
"self": 0.0,
"children": {
"worker_root": {
"total": 2489.91435687004,
"count": 232481,
"is_parallel": true,
"self": 1189.925157469014,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008554579999326961,
"count": 1,
"is_parallel": true,
"self": 0.00023055599979215913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000624902000140537,
"count": 2,
"is_parallel": true,
"self": 0.000624902000140537
}
}
},
"UnityEnvironment.step": {
"total": 0.028515175999928033,
"count": 1,
"is_parallel": true,
"self": 0.00029809399995883723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020391600003222266,
"count": 1,
"is_parallel": true,
"self": 0.00020391600003222266
},
"communicator.exchange": {
"total": 0.027339669999946636,
"count": 1,
"is_parallel": true,
"self": 0.027339669999946636
},
"steps_from_proto": {
"total": 0.0006734959999903367,
"count": 1,
"is_parallel": true,
"self": 0.00018025200006377418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004932439999265625,
"count": 2,
"is_parallel": true,
"self": 0.0004932439999265625
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.989199401026,
"count": 232480,
"is_parallel": true,
"self": 39.63354113205014,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.66029107096324,
"count": 232480,
"is_parallel": true,
"self": 80.66029107096324
},
"communicator.exchange": {
"total": 1092.5049697189447,
"count": 232480,
"is_parallel": true,
"self": 1092.5049697189447
},
"steps_from_proto": {
"total": 87.190397479068,
"count": 232480,
"is_parallel": true,
"self": 30.405087278078895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.7853102009891,
"count": 464960,
"is_parallel": true,
"self": 56.7853102009891
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.7718166520782,
"count": 232481,
"self": 6.628026580024425,
"children": {
"process_trajectory": {
"total": 158.24572489805428,
"count": 232481,
"self": 157.11402394405445,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1317009539998253,
"count": 10,
"self": 1.1317009539998253
}
}
},
"_update_policy": {
"total": 365.8980651739995,
"count": 97,
"self": 301.5890489060139,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.30901626798561,
"count": 2910,
"self": 64.30901626798561
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1800002539530396e-06,
"count": 1,
"self": 1.1800002539530396e-06
},
"TrainerController._save_models": {
"total": 0.10408405499993023,
"count": 1,
"self": 0.0017781579999791575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10230589699995107,
"count": 1,
"self": 0.10230589699995107
}
}
}
}
}
}
}