ppo-Huggy / run_logs /timers.json
dragovoid's picture
Huggy
18dcb4b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403343677520752,
"min": 1.403343677520752,
"max": 1.4278838634490967,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68201.1015625,
"min": 67937.0859375,
"max": 77528.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 134.34417344173443,
"min": 99.5271629778672,
"max": 394.8217054263566,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49573.0,
"min": 48920.0,
"max": 50932.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49621.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49621.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2082700729370117,
"min": -0.01941036991775036,
"max": 2.389754295349121,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 814.8516845703125,
"min": -2.4651169776916504,
"max": 1169.803466796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3227055145473017,
"min": 1.7165286484665758,
"max": 3.8285601204848505,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1226.0783348679543,
"min": 217.99913835525513,
"max": 1843.5543966889381,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3227055145473017,
"min": 1.7165286484665758,
"max": 3.8285601204848505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1226.0783348679543,
"min": 217.99913835525513,
"max": 1843.5543966889381,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01398979675238176,
"min": 0.01212709230215599,
"max": 0.021695971954613924,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02797959350476352,
"min": 0.02425418460431198,
"max": 0.05531776941837355,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04068676096697648,
"min": 0.022738481406122446,
"max": 0.0714520978430907,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08137352193395296,
"min": 0.04547696281224489,
"max": 0.20274453423917294,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.525748491450008e-06,
"min": 4.525748491450008e-06,
"max": 0.00029534985155004996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.051496982900016e-06,
"min": 9.051496982900016e-06,
"max": 0.0008441881686039499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10150855000000003,
"min": 0.10150855000000003,
"max": 0.19844995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20301710000000006,
"min": 0.20301710000000006,
"max": 0.5813960499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.527664500000015e-05,
"min": 8.527664500000015e-05,
"max": 0.004922652505,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001705532900000003,
"min": 0.0001705532900000003,
"max": 0.014071662894999998,
"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": "1732389705",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732392285"
},
"total": 2579.476631958,
"count": 1,
"self": 0.43234300199992504,
"children": {
"run_training.setup": {
"total": 0.06772706599986122,
"count": 1,
"self": 0.06772706599986122
},
"TrainerController.start_learning": {
"total": 2578.97656189,
"count": 1,
"self": 4.770061004031049,
"children": {
"TrainerController._reset_env": {
"total": 4.928753113999846,
"count": 1,
"self": 4.928753113999846
},
"TrainerController.advance": {
"total": 2569.162439487969,
"count": 230629,
"self": 4.9156767718482115,
"children": {
"env_step": {
"total": 2037.6425823630466,
"count": 230629,
"self": 1600.8885453770774,
"children": {
"SubprocessEnvManager._take_step": {
"total": 433.7287765749877,
"count": 230629,
"self": 16.456419502065955,
"children": {
"TorchPolicy.evaluate": {
"total": 417.27235707292175,
"count": 222972,
"self": 417.27235707292175
}
}
},
"workers": {
"total": 3.0252604109814456,
"count": 230629,
"self": 0.0,
"children": {
"worker_root": {
"total": 2571.242548715997,
"count": 230629,
"is_parallel": true,
"self": 1271.4772034159685,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000890454000000318,
"count": 1,
"is_parallel": true,
"self": 0.00025927899991984305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000631175000080475,
"count": 2,
"is_parallel": true,
"self": 0.000631175000080475
}
}
},
"UnityEnvironment.step": {
"total": 0.02988176500002737,
"count": 1,
"is_parallel": true,
"self": 0.00038690500014126883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019979900002908835,
"count": 1,
"is_parallel": true,
"self": 0.00019979900002908835
},
"communicator.exchange": {
"total": 0.028454068999963056,
"count": 1,
"is_parallel": true,
"self": 0.028454068999963056
},
"steps_from_proto": {
"total": 0.0008409919998939586,
"count": 1,
"is_parallel": true,
"self": 0.00020801199980269303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006329800000912655,
"count": 2,
"is_parallel": true,
"self": 0.0006329800000912655
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.7653453000287,
"count": 230628,
"is_parallel": true,
"self": 39.174874635032666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.33779099301455,
"count": 230628,
"is_parallel": true,
"self": 87.33779099301455
},
"communicator.exchange": {
"total": 1080.6213240640768,
"count": 230628,
"is_parallel": true,
"self": 1080.6213240640768
},
"steps_from_proto": {
"total": 92.63135560790465,
"count": 230628,
"is_parallel": true,
"self": 34.52453695280201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.10681865510264,
"count": 461256,
"is_parallel": true,
"self": 58.10681865510264
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 526.6041803530743,
"count": 230629,
"self": 7.135875337021389,
"children": {
"process_trajectory": {
"total": 163.43346094205504,
"count": 230629,
"self": 162.1441101780547,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2893507640003463,
"count": 10,
"self": 1.2893507640003463
}
}
},
"_update_policy": {
"total": 356.0348440739979,
"count": 96,
"self": 287.01262695898663,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.02221711501124,
"count": 2880,
"self": 69.02221711501124
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.770002750679851e-07,
"count": 1,
"self": 8.770002750679851e-07
},
"TrainerController._save_models": {
"total": 0.11530740699981834,
"count": 1,
"self": 0.002480230999935884,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11282717599988246,
"count": 1,
"self": 0.11282717599988246
}
}
}
}
}
}
}