ppo-Huggy / run_logs /timers.json
OrionChang's picture
Huggy
d0b446b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4121026992797852,
"min": 1.4120994806289673,
"max": 1.4299869537353516,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70088.3046875,
"min": 68241.3515625,
"max": 77476.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 109.46,
"min": 87.51681415929204,
"max": 377.97727272727275,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49257.0,
"min": 49088.0,
"max": 50075.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999888.0,
"min": 49448.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999888.0,
"min": 49448.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.309828042984009,
"min": 0.07259208709001541,
"max": 2.430403232574463,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1039.422607421875,
"min": 9.509563446044922,
"max": 1318.18408203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.53041120979521,
"min": 1.9647371354903884,
"max": 3.8895057891312703,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1588.6850444078445,
"min": 257.3805647492409,
"max": 2144.4687650203705,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.53041120979521,
"min": 1.9647371354903884,
"max": 3.8895057891312703,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1588.6850444078445,
"min": 257.3805647492409,
"max": 2144.4687650203705,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015046576884277683,
"min": 0.014289849499861399,
"max": 0.01906071659177542,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04513973065283305,
"min": 0.028579698999722798,
"max": 0.055474239261820914,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04732477851212025,
"min": 0.023289263703756863,
"max": 0.06000606926778953,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14197433553636074,
"min": 0.04718031032631795,
"max": 0.18001820780336858,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4257988581000098e-06,
"min": 3.4257988581000098e-06,
"max": 0.00029538382653872497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0277396574300029e-05,
"min": 1.0277396574300029e-05,
"max": 0.0008441409186196999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114189999999997,
"min": 0.10114189999999997,
"max": 0.19846127500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034256999999999,
"min": 0.20747154999999995,
"max": 0.5813803000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.698081000000015e-05,
"min": 6.698081000000015e-05,
"max": 0.0049232176225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020094243000000047,
"min": 0.00020094243000000047,
"max": 0.01407087697,
"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": "1743604745",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743607243"
},
"total": 2497.642186613,
"count": 1,
"self": 0.44218966999960685,
"children": {
"run_training.setup": {
"total": 0.02303662600024836,
"count": 1,
"self": 0.02303662600024836
},
"TrainerController.start_learning": {
"total": 2497.176960317,
"count": 1,
"self": 4.4879568658670905,
"children": {
"TrainerController._reset_env": {
"total": 3.520970008000404,
"count": 1,
"self": 3.520970008000404
},
"TrainerController.advance": {
"total": 2489.0519435461333,
"count": 231702,
"self": 4.510920869386609,
"children": {
"env_step": {
"total": 2002.804639065885,
"count": 231702,
"self": 1567.0127910387737,
"children": {
"SubprocessEnvManager._take_step": {
"total": 433.0580568220553,
"count": 231702,
"self": 15.958614819094691,
"children": {
"TorchPolicy.evaluate": {
"total": 417.0994420029606,
"count": 222922,
"self": 417.0994420029606
}
}
},
"workers": {
"total": 2.73379120505615,
"count": 231702,
"self": 0.0,
"children": {
"worker_root": {
"total": 2489.421377476035,
"count": 231702,
"is_parallel": true,
"self": 1211.3950968549389,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010407320000922482,
"count": 1,
"is_parallel": true,
"self": 0.0002467509998496098,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007939810002426384,
"count": 2,
"is_parallel": true,
"self": 0.0007939810002426384
}
}
},
"UnityEnvironment.step": {
"total": 0.05683674800002336,
"count": 1,
"is_parallel": true,
"self": 0.0003453700001045945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020627399999284535,
"count": 1,
"is_parallel": true,
"self": 0.00020627399999284535
},
"communicator.exchange": {
"total": 0.055564954999681504,
"count": 1,
"is_parallel": true,
"self": 0.055564954999681504
},
"steps_from_proto": {
"total": 0.0007201490002444189,
"count": 1,
"is_parallel": true,
"self": 0.0002121430002262059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005080060000182129,
"count": 2,
"is_parallel": true,
"self": 0.0005080060000182129
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.0262806210962,
"count": 231701,
"is_parallel": true,
"self": 37.60916663897024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.86031055208878,
"count": 231701,
"is_parallel": true,
"self": 82.86031055208878
},
"communicator.exchange": {
"total": 1068.9823971491455,
"count": 231701,
"is_parallel": true,
"self": 1068.9823971491455
},
"steps_from_proto": {
"total": 88.57440628089171,
"count": 231701,
"is_parallel": true,
"self": 32.82622526384512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.74818101704659,
"count": 463402,
"is_parallel": true,
"self": 55.74818101704659
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.7363836108616,
"count": 231702,
"self": 7.025952878912449,
"children": {
"process_trajectory": {
"total": 165.22186814694305,
"count": 231702,
"self": 163.79425460494258,
"children": {
"RLTrainer._checkpoint": {
"total": 1.427613542000472,
"count": 10,
"self": 1.427613542000472
}
}
},
"_update_policy": {
"total": 309.4885625850061,
"count": 97,
"self": 245.65011707100393,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.83844551400216,
"count": 2910,
"self": 63.83844551400216
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.939996405388229e-07,
"count": 1,
"self": 8.939996405388229e-07
},
"TrainerController._save_models": {
"total": 0.11608900299961533,
"count": 1,
"self": 0.002104502999827673,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11398449999978766,
"count": 1,
"self": 0.11398449999978766
}
}
}
}
}
}
}