ppo-Huggy / run_logs /timers.json
bjpsantos's picture
Huggy
4661024
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4105287790298462,
"min": 1.4105287790298462,
"max": 1.427003264427185,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70193.5546875,
"min": 68365.8671875,
"max": 78168.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.34920634920636,
"min": 74.73484848484848,
"max": 369.45185185185187,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49360.0,
"min": 48669.0,
"max": 50036.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49886.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49886.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5186657905578613,
"min": 0.09652551263570786,
"max": 2.5186657905578613,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1586.759521484375,
"min": 13.127470016479492,
"max": 1622.793212890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9712726523005775,
"min": 1.7301150268929846,
"max": 4.024853588859307,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2501.9017709493637,
"min": 235.2956436574459,
"max": 2505.668896853924,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9712726523005775,
"min": 1.7301150268929846,
"max": 4.024853588859307,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2501.9017709493637,
"min": 235.2956436574459,
"max": 2505.668896853924,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01743607443046737,
"min": 0.0132064024117426,
"max": 0.022148759058109136,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052308223291402105,
"min": 0.0264128048234852,
"max": 0.05521203211974353,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055797830141252946,
"min": 0.02118114416177074,
"max": 0.06686211060732603,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16739349042375884,
"min": 0.04236228832354148,
"max": 0.17688428945839405,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.707448764216666e-06,
"min": 3.707448764216666e-06,
"max": 0.00029531557656147493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1122346292649998e-05,
"min": 1.1122346292649998e-05,
"max": 0.0008441172186276001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123578333333333,
"min": 0.10123578333333333,
"max": 0.19843852499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30370735,
"min": 0.20760275,
"max": 0.5813724000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.166558833333329e-05,
"min": 7.166558833333329e-05,
"max": 0.004922082397499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021499676499999988,
"min": 0.00021499676499999988,
"max": 0.01407048276,
"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": "1673454751",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.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": "1673456926"
},
"total": 2174.759543926,
"count": 1,
"self": 0.3876021139999466,
"children": {
"run_training.setup": {
"total": 0.11229681899999377,
"count": 1,
"self": 0.11229681899999377
},
"TrainerController.start_learning": {
"total": 2174.259644993,
"count": 1,
"self": 3.637495599999511,
"children": {
"TrainerController._reset_env": {
"total": 7.673638118999861,
"count": 1,
"self": 7.673638118999861
},
"TrainerController.advance": {
"total": 2162.8348601880007,
"count": 232829,
"self": 3.776690117988437,
"children": {
"env_step": {
"total": 1695.5637006469537,
"count": 232829,
"self": 1428.5703123600483,
"children": {
"SubprocessEnvManager._take_step": {
"total": 264.38925439194395,
"count": 232829,
"self": 13.933211703001916,
"children": {
"TorchPolicy.evaluate": {
"total": 250.45604268894203,
"count": 222919,
"self": 62.71896190783241,
"children": {
"TorchPolicy.sample_actions": {
"total": 187.73708078110963,
"count": 222919,
"self": 187.73708078110963
}
}
}
}
},
"workers": {
"total": 2.6041338949614783,
"count": 232829,
"self": 0.0,
"children": {
"worker_root": {
"total": 2166.7732357879745,
"count": 232829,
"is_parallel": true,
"self": 989.667506905043,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020419079999101086,
"count": 1,
"is_parallel": true,
"self": 0.0003392479998183262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017026600000917824,
"count": 2,
"is_parallel": true,
"self": 0.0017026600000917824
}
}
},
"UnityEnvironment.step": {
"total": 0.026216574999807563,
"count": 1,
"is_parallel": true,
"self": 0.00029306400006134936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019486399992274528,
"count": 1,
"is_parallel": true,
"self": 0.00019486399992274528
},
"communicator.exchange": {
"total": 0.024843767999982447,
"count": 1,
"is_parallel": true,
"self": 0.024843767999982447
},
"steps_from_proto": {
"total": 0.0008848789998410211,
"count": 1,
"is_parallel": true,
"self": 0.00041899899974850996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004658800000925112,
"count": 2,
"is_parallel": true,
"self": 0.0004658800000925112
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1177.1057288829315,
"count": 232828,
"is_parallel": true,
"self": 33.95334850185236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.67691639793225,
"count": 232828,
"is_parallel": true,
"self": 74.67691639793225
},
"communicator.exchange": {
"total": 977.28371492307,
"count": 232828,
"is_parallel": true,
"self": 977.28371492307
},
"steps_from_proto": {
"total": 91.19174906007697,
"count": 232828,
"is_parallel": true,
"self": 37.16437409914738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.02737496092959,
"count": 465656,
"is_parallel": true,
"self": 54.02737496092959
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 463.4944694230585,
"count": 232829,
"self": 5.832206336075615,
"children": {
"process_trajectory": {
"total": 146.60310968998283,
"count": 232829,
"self": 145.43390570398356,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1692039859992747,
"count": 10,
"self": 1.1692039859992747
}
}
},
"_update_policy": {
"total": 311.05915339700005,
"count": 97,
"self": 258.3015022480024,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.75765114899764,
"count": 2910,
"self": 52.75765114899764
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.380000847158954e-07,
"count": 1,
"self": 9.380000847158954e-07
},
"TrainerController._save_models": {
"total": 0.11365014800003337,
"count": 1,
"self": 0.002062428000044747,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11158771999998862,
"count": 1,
"self": 0.11158771999998862
}
}
}
}
}
}
}