ppo-Huggy / run_logs /timers.json
andreaostuni's picture
Huggy
bb8b7e3 verified
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4041498899459839,
"min": 1.4041498899459839,
"max": 1.4247560501098633,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71364.515625,
"min": 69284.78125,
"max": 76813.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.21439509954058,
"min": 72.3782991202346,
"max": 388.3333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49768.0,
"min": 49266.0,
"max": 50095.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999732.0,
"min": 49835.0,
"max": 1999732.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999732.0,
"min": 49835.0,
"max": 1999732.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5257697105407715,
"min": 0.010340871289372444,
"max": 2.5486674308776855,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1649.32763671875,
"min": 1.3236315250396729,
"max": 1721.271240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9431415833703958,
"min": 1.7654419302707538,
"max": 4.028626342261279,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2574.8714539408684,
"min": 225.9765670746565,
"max": 2719.3227810263634,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9431415833703958,
"min": 1.7654419302707538,
"max": 4.028626342261279,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2574.8714539408684,
"min": 225.9765670746565,
"max": 2719.3227810263634,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015981197090392623,
"min": 0.014194234525590824,
"max": 0.020436129405667698,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047943591271177866,
"min": 0.02838846905118165,
"max": 0.057784861962621406,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05961692647801505,
"min": 0.023840193284882443,
"max": 0.06775071478138367,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17885077943404515,
"min": 0.050344058126211164,
"max": 0.18826758141318958,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6255487915166638e-06,
"min": 3.6255487915166638e-06,
"max": 0.00029531820156059995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0876646374549991e-05,
"min": 1.0876646374549991e-05,
"max": 0.0008439828186723999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120848333333332,
"min": 0.10120848333333332,
"max": 0.1984394,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362544999999996,
"min": 0.20754299999999998,
"max": 0.5813276000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.030331833333331e-05,
"min": 7.030331833333331e-05,
"max": 0.00492212606,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002109099549999999,
"min": 0.0002109099549999999,
"max": 0.014068247239999998,
"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": "1714121952",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714124344"
},
"total": 2391.700385223,
"count": 1,
"self": 0.4306171110001742,
"children": {
"run_training.setup": {
"total": 0.05655541999999514,
"count": 1,
"self": 0.05655541999999514
},
"TrainerController.start_learning": {
"total": 2391.213212692,
"count": 1,
"self": 4.242629935954028,
"children": {
"TrainerController._reset_env": {
"total": 2.9088931090000187,
"count": 1,
"self": 2.9088931090000187
},
"TrainerController.advance": {
"total": 2383.934329710046,
"count": 233324,
"self": 4.554255666942936,
"children": {
"env_step": {
"total": 1879.6388366840997,
"count": 233324,
"self": 1564.3055390562706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.5540468678704,
"count": 233324,
"self": 17.51518748574256,
"children": {
"TorchPolicy.evaluate": {
"total": 295.03885938212784,
"count": 222971,
"self": 295.03885938212784
}
}
},
"workers": {
"total": 2.7792507599586997,
"count": 233324,
"self": 0.0,
"children": {
"worker_root": {
"total": 2384.07712117811,
"count": 233324,
"is_parallel": true,
"self": 1118.2876614151369,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008786799999143113,
"count": 1,
"is_parallel": true,
"self": 0.0002221450000661207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006565349998481906,
"count": 2,
"is_parallel": true,
"self": 0.0006565349998481906
}
}
},
"UnityEnvironment.step": {
"total": 0.05262903899995308,
"count": 1,
"is_parallel": true,
"self": 0.0004142499999488791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021271000002798246,
"count": 1,
"is_parallel": true,
"self": 0.00021271000002798246
},
"communicator.exchange": {
"total": 0.05118924700002481,
"count": 1,
"is_parallel": true,
"self": 0.05118924700002481
},
"steps_from_proto": {
"total": 0.0008128319999514133,
"count": 1,
"is_parallel": true,
"self": 0.00021024299996952323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006025889999818901,
"count": 2,
"is_parallel": true,
"self": 0.0006025889999818901
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1265.789459762973,
"count": 233323,
"is_parallel": true,
"self": 39.28680582896868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.27104445797067,
"count": 233323,
"is_parallel": true,
"self": 81.27104445797067
},
"communicator.exchange": {
"total": 1054.4719765050188,
"count": 233323,
"is_parallel": true,
"self": 1054.4719765050188
},
"steps_from_proto": {
"total": 90.75963297101475,
"count": 233323,
"is_parallel": true,
"self": 32.538353853001354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.2212791180134,
"count": 466646,
"is_parallel": true,
"self": 58.2212791180134
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.7412373590031,
"count": 233324,
"self": 6.412384835105172,
"children": {
"process_trajectory": {
"total": 153.56999588689814,
"count": 233324,
"self": 152.27987584089874,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2901200459994016,
"count": 10,
"self": 1.2901200459994016
}
}
},
"_update_policy": {
"total": 339.7588566369998,
"count": 97,
"self": 276.40113079701143,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.35772583998835,
"count": 2910,
"self": 63.35772583998835
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.910001270123757e-07,
"count": 1,
"self": 8.910001270123757e-07
},
"TrainerController._save_models": {
"total": 0.12735904600003778,
"count": 1,
"self": 0.0032826259998728347,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12407642000016494,
"count": 1,
"self": 0.12407642000016494
}
}
}
}
}
}
}