ppo-Huggy / run_logs /timers.json
songyizhao's picture
Huggy
6a7a82c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3998711109161377,
"min": 1.3998711109161377,
"max": 1.426073431968689,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68551.6875,
"min": 67937.21875,
"max": 77666.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.46915887850467,
"min": 72.67304860088365,
"max": 420.675,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49471.0,
"min": 49181.0,
"max": 50481.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49946.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49946.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4525973796844482,
"min": 0.1270882487297058,
"max": 2.5267536640167236,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1312.1396484375,
"min": 15.123501777648926,
"max": 1709.20068359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7593636486017816,
"min": 1.7763521410837895,
"max": 4.0123103640296245,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2011.2595520019531,
"min": 211.38590478897095,
"max": 2689.9936393499374,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7593636486017816,
"min": 1.7763521410837895,
"max": 4.0123103640296245,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2011.2595520019531,
"min": 211.38590478897095,
"max": 2689.9936393499374,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01838556851437008,
"min": 0.012620759145647753,
"max": 0.02003758747402268,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05515670554311024,
"min": 0.025241518291295506,
"max": 0.055416991329790714,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04811769864625401,
"min": 0.021173789010693632,
"max": 0.058220907424887024,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14435309593876203,
"min": 0.042347578021387264,
"max": 0.17466272227466106,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.898498700533324e-06,
"min": 3.898498700533324e-06,
"max": 0.000295350526549825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1695496101599973e-05,
"min": 1.1695496101599973e-05,
"max": 0.0008442606185797999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129946666666667,
"min": 0.10129946666666667,
"max": 0.198450175,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038984,
"min": 0.20783495000000002,
"max": 0.5814202,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.484338666666654e-05,
"min": 7.484338666666654e-05,
"max": 0.0049226637325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022453015999999962,
"min": 0.00022453015999999962,
"max": 0.01407286798,
"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": "1679925316",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "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": "1679927661"
},
"total": 2345.0894386970003,
"count": 1,
"self": 0.44500300000072457,
"children": {
"run_training.setup": {
"total": 0.16852012300000752,
"count": 1,
"self": 0.16852012300000752
},
"TrainerController.start_learning": {
"total": 2344.475915574,
"count": 1,
"self": 4.4185151840601975,
"children": {
"TrainerController._reset_env": {
"total": 9.548091831000079,
"count": 1,
"self": 9.548091831000079
},
"TrainerController.advance": {
"total": 2330.39982250294,
"count": 233083,
"self": 4.497401314875333,
"children": {
"env_step": {
"total": 1813.1608751530366,
"count": 233083,
"self": 1528.8471555519563,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.4924940290625,
"count": 233083,
"self": 17.448415530967623,
"children": {
"TorchPolicy.evaluate": {
"total": 264.0440784980949,
"count": 222947,
"self": 264.0440784980949
}
}
},
"workers": {
"total": 2.821225572017738,
"count": 233083,
"self": 0.0,
"children": {
"worker_root": {
"total": 2336.5901397480206,
"count": 233083,
"is_parallel": true,
"self": 1094.647293813054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011220399999274377,
"count": 1,
"is_parallel": true,
"self": 0.00028510700008155254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008369329998458852,
"count": 2,
"is_parallel": true,
"self": 0.0008369329998458852
}
}
},
"UnityEnvironment.step": {
"total": 0.02924904999986211,
"count": 1,
"is_parallel": true,
"self": 0.00030741899990971433,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019570799986468046,
"count": 1,
"is_parallel": true,
"self": 0.00019570799986468046
},
"communicator.exchange": {
"total": 0.028018270000075063,
"count": 1,
"is_parallel": true,
"self": 0.028018270000075063
},
"steps_from_proto": {
"total": 0.0007276530000126513,
"count": 1,
"is_parallel": true,
"self": 0.00020665400006691925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005209989999457321,
"count": 2,
"is_parallel": true,
"self": 0.0005209989999457321
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1241.9428459349667,
"count": 233082,
"is_parallel": true,
"self": 38.468685169868195,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.32957513313113,
"count": 233082,
"is_parallel": true,
"self": 76.32957513313113
},
"communicator.exchange": {
"total": 1037.9429637200003,
"count": 233082,
"is_parallel": true,
"self": 1037.9429637200003
},
"steps_from_proto": {
"total": 89.2016219119671,
"count": 233082,
"is_parallel": true,
"self": 33.45526978599469,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.74635212597241,
"count": 466164,
"is_parallel": true,
"self": 55.74635212597241
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 512.741546035028,
"count": 233083,
"self": 6.632679556002813,
"children": {
"process_trajectory": {
"total": 144.89841373902595,
"count": 233083,
"self": 143.49771883002586,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4006949090000944,
"count": 10,
"self": 1.4006949090000944
}
}
},
"_update_policy": {
"total": 361.21045273999925,
"count": 97,
"self": 303.0782367849938,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.13221595500545,
"count": 2910,
"self": 58.13221595500545
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0369999472459313e-06,
"count": 1,
"self": 1.0369999472459313e-06
},
"TrainerController._save_models": {
"total": 0.10948501899974872,
"count": 1,
"self": 0.0018847739993361756,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10760024500041254,
"count": 1,
"self": 0.10760024500041254
}
}
}
}
}
}
}