ppo-Huggy / run_logs /timers.json
AdanLee's picture
Huggy
e9a25bd
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408448338508606,
"min": 1.408448338508606,
"max": 1.4293409585952759,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70036.5,
"min": 69316.7265625,
"max": 77816.9765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.40250447227191,
"min": 81.25164473684211,
"max": 409.72131147540983,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49417.0,
"min": 48984.0,
"max": 50192.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49919.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49919.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.418139934539795,
"min": 0.14358198642730713,
"max": 2.480660915374756,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1351.740234375,
"min": 17.37342071533203,
"max": 1466.279296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8012176707307,
"min": 1.720286963646077,
"max": 3.950565675130257,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2124.8806779384613,
"min": 208.1547226011753,
"max": 2305.598359644413,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8012176707307,
"min": 1.720286963646077,
"max": 3.950565675130257,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2124.8806779384613,
"min": 208.1547226011753,
"max": 2305.598359644413,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018358501254988367,
"min": 0.014435367231878143,
"max": 0.021246054599760103,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0550755037649651,
"min": 0.028870734463756285,
"max": 0.0565281834404838,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05724794252051247,
"min": 0.020774695556610823,
"max": 0.06200883396797711,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17174382756153742,
"min": 0.041549391113221645,
"max": 0.18602650190393133,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.594748801783333e-06,
"min": 3.594748801783333e-06,
"max": 0.00029525400158199994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0784246405349999e-05,
"min": 1.0784246405349999e-05,
"max": 0.0008438653687115497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119821666666666,
"min": 0.10119821666666666,
"max": 0.19841800000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30359464999999997,
"min": 0.2075441500000001,
"max": 0.5812884500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.979101166666665e-05,
"min": 6.979101166666665e-05,
"max": 0.004921058200000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020937303499999997,
"min": 0.00020937303499999997,
"max": 0.014066293655000001,
"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": "1689387499",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689389976"
},
"total": 2476.37004788,
"count": 1,
"self": 0.4899870019999071,
"children": {
"run_training.setup": {
"total": 0.05110700400001633,
"count": 1,
"self": 0.05110700400001633
},
"TrainerController.start_learning": {
"total": 2475.828953874,
"count": 1,
"self": 4.349599342994225,
"children": {
"TrainerController._reset_env": {
"total": 4.141284502000019,
"count": 1,
"self": 4.141284502000019
},
"TrainerController.advance": {
"total": 2467.2059387530057,
"count": 232240,
"self": 4.576349412066975,
"children": {
"env_step": {
"total": 1911.840459008011,
"count": 232240,
"self": 1614.0040922680184,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.9397034250293,
"count": 232240,
"self": 17.674370324093275,
"children": {
"TorchPolicy.evaluate": {
"total": 277.265333100936,
"count": 222976,
"self": 277.265333100936
}
}
},
"workers": {
"total": 2.896663314963291,
"count": 232240,
"self": 0.0,
"children": {
"worker_root": {
"total": 2468.0463383390183,
"count": 232240,
"is_parallel": true,
"self": 1147.1623902110564,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008605040000020381,
"count": 1,
"is_parallel": true,
"self": 0.00024266799999850264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006178360000035354,
"count": 2,
"is_parallel": true,
"self": 0.0006178360000035354
}
}
},
"UnityEnvironment.step": {
"total": 0.029333059999999023,
"count": 1,
"is_parallel": true,
"self": 0.0003526990000182195,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022229900002912473,
"count": 1,
"is_parallel": true,
"self": 0.00022229900002912473
},
"communicator.exchange": {
"total": 0.027947429999983342,
"count": 1,
"is_parallel": true,
"self": 0.027947429999983342
},
"steps_from_proto": {
"total": 0.0008106319999683365,
"count": 1,
"is_parallel": true,
"self": 0.00025688499994203084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005537470000263056,
"count": 2,
"is_parallel": true,
"self": 0.0005537470000263056
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1320.883948127962,
"count": 232239,
"is_parallel": true,
"self": 41.65922783490805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.24845190411014,
"count": 232239,
"is_parallel": true,
"self": 82.24845190411014
},
"communicator.exchange": {
"total": 1095.5957800930087,
"count": 232239,
"is_parallel": true,
"self": 1095.5957800930087
},
"steps_from_proto": {
"total": 101.38048829593498,
"count": 232239,
"is_parallel": true,
"self": 35.44548565282997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.93500264310501,
"count": 464478,
"is_parallel": true,
"self": 65.93500264310501
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 550.7891303329279,
"count": 232240,
"self": 6.943097610975201,
"children": {
"process_trajectory": {
"total": 140.71498818995218,
"count": 232240,
"self": 139.29244229895193,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4225458910002544,
"count": 10,
"self": 1.4225458910002544
}
}
},
"_update_policy": {
"total": 403.1310445320005,
"count": 97,
"self": 340.93689693700685,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.19414759499364,
"count": 2910,
"self": 62.19414759499364
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.189998309011571e-07,
"count": 1,
"self": 9.189998309011571e-07
},
"TrainerController._save_models": {
"total": 0.1321303570002783,
"count": 1,
"self": 0.0025359050000588468,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12959445200021946,
"count": 1,
"self": 0.12959445200021946
}
}
}
}
}
}
}