ppo-Huggy / run_logs /timers.json
lnros's picture
Huggy
a0f3968
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4061616659164429,
"min": 1.4061616659164429,
"max": 1.4280333518981934,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69642.96875,
"min": 68384.0546875,
"max": 78274.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.30703259005146,
"min": 73.8443113772455,
"max": 397.1031746031746,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49151.0,
"min": 48676.0,
"max": 50041.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49802.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49802.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4005703926086426,
"min": 0.04090219363570213,
"max": 2.470264196395874,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1399.532470703125,
"min": 5.11277437210083,
"max": 1610.6123046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7160205246040383,
"min": 1.753625426530838,
"max": 4.077400167817836,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2166.4399658441544,
"min": 219.20317831635475,
"max": 2607.0156088471413,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7160205246040383,
"min": 1.753625426530838,
"max": 4.077400167817836,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2166.4399658441544,
"min": 219.20317831635475,
"max": 2607.0156088471413,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01747614027828806,
"min": 0.012569055937880573,
"max": 0.020193918581935574,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05242842083486418,
"min": 0.025138111875761145,
"max": 0.05734680018140352,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052573024522927066,
"min": 0.022662868288656074,
"max": 0.06473105742285648,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1577190735687812,
"min": 0.04532573657731215,
"max": 0.18282639992733796,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.736698754466679e-06,
"min": 3.736698754466679e-06,
"max": 0.000295322176559275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1210096263400037e-05,
"min": 1.1210096263400037e-05,
"max": 0.0008441737686087497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124553333333335,
"min": 0.10124553333333335,
"max": 0.19844072499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037366,
"min": 0.20762149999999996,
"max": 0.5813912499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.215211333333356e-05,
"min": 7.215211333333356e-05,
"max": 0.004922192177500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021645634000000066,
"min": 0.00021645634000000066,
"max": 0.014071423374999998,
"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": "1670678730",
"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": "1670680952"
},
"total": 2221.341448158,
"count": 1,
"self": 0.44091516099979344,
"children": {
"run_training.setup": {
"total": 0.11413158699997439,
"count": 1,
"self": 0.11413158699997439
},
"TrainerController.start_learning": {
"total": 2220.78640141,
"count": 1,
"self": 3.7641519010280717,
"children": {
"TrainerController._reset_env": {
"total": 10.936627600999941,
"count": 1,
"self": 10.936627600999941
},
"TrainerController.advance": {
"total": 2205.9732349259716,
"count": 233098,
"self": 4.145656260928263,
"children": {
"env_step": {
"total": 1729.2772417520644,
"count": 233098,
"self": 1450.4070403798273,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.2992066270773,
"count": 233098,
"self": 14.46862011015412,
"children": {
"TorchPolicy.evaluate": {
"total": 261.8305865169232,
"count": 222980,
"self": 66.16869301388056,
"children": {
"TorchPolicy.sample_actions": {
"total": 195.66189350304262,
"count": 222980,
"self": 195.66189350304262
}
}
}
}
},
"workers": {
"total": 2.5709947451596236,
"count": 233098,
"self": 0.0,
"children": {
"worker_root": {
"total": 2212.9230706789044,
"count": 233098,
"is_parallel": true,
"self": 1018.6898430779834,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021133259999714937,
"count": 1,
"is_parallel": true,
"self": 0.0002819400000362293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018313859999352644,
"count": 2,
"is_parallel": true,
"self": 0.0018313859999352644
}
}
},
"UnityEnvironment.step": {
"total": 0.028767076000008274,
"count": 1,
"is_parallel": true,
"self": 0.0002670760001137751,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021950999996533938,
"count": 1,
"is_parallel": true,
"self": 0.00021950999996533938
},
"communicator.exchange": {
"total": 0.02760349100003623,
"count": 1,
"is_parallel": true,
"self": 0.02760349100003623
},
"steps_from_proto": {
"total": 0.0006769989998929304,
"count": 1,
"is_parallel": true,
"self": 0.00022867600000608945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000448322999886841,
"count": 2,
"is_parallel": true,
"self": 0.000448322999886841
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1194.233227600921,
"count": 233097,
"is_parallel": true,
"self": 34.47676173182208,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.74945499601381,
"count": 233097,
"is_parallel": true,
"self": 75.74945499601381
},
"communicator.exchange": {
"total": 992.1032602329825,
"count": 233097,
"is_parallel": true,
"self": 992.1032602329825
},
"steps_from_proto": {
"total": 91.90375064010277,
"count": 233097,
"is_parallel": true,
"self": 37.61797277611845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.28577786398432,
"count": 466194,
"is_parallel": true,
"self": 54.28577786398432
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.5503369129789,
"count": 233098,
"self": 5.901813546015887,
"children": {
"process_trajectory": {
"total": 153.14773965496602,
"count": 233098,
"self": 152.67354252296604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47419713199997204,
"count": 4,
"self": 0.47419713199997204
}
}
},
"_update_policy": {
"total": 313.500783711997,
"count": 97,
"self": 259.4847181679944,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.01606554400257,
"count": 2910,
"self": 54.01606554400257
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.530000741302501e-07,
"count": 1,
"self": 8.530000741302501e-07
},
"TrainerController._save_models": {
"total": 0.11238612900024236,
"count": 1,
"self": 0.0019838230005007063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11040230599974166,
"count": 1,
"self": 0.11040230599974166
}
}
}
}
}
}
}