ppo-Huggy / run_logs /timers.json
jcorblaz's picture
Huggy
22c213b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3999723196029663,
"min": 1.3999723196029663,
"max": 1.4277750253677368,
"count": 30
},
"Huggy.Policy.Entropy.sum": {
"value": 69886.6171875,
"min": 68786.9609375,
"max": 76717.5390625,
"count": 30
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.0915750915751,
"min": 84.41438356164383,
"max": 384.25384615384615,
"count": 30
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48644.0,
"min": 48644.0,
"max": 50232.0,
"count": 30
},
"Huggy.Step.mean": {
"value": 1499927.0,
"min": 49765.0,
"max": 1499927.0,
"count": 30
},
"Huggy.Step.sum": {
"value": 1499927.0,
"min": 49765.0,
"max": 1499927.0,
"count": 30
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4505605697631836,
"min": 0.19367890059947968,
"max": 2.4505605697631836,
"count": 30
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1342.9072265625,
"min": 24.98457908630371,
"max": 1401.873046875,
"count": 30
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8369713609453537,
"min": 1.8307592122591743,
"max": 3.941207455471158,
"count": 30
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2102.6603057980537,
"min": 236.1679383814335,
"max": 2241.5967559814453,
"count": 30
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8369713609453537,
"min": 1.8307592122591743,
"max": 3.941207455471158,
"count": 30
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2102.6603057980537,
"min": 236.1679383814335,
"max": 2241.5967559814453,
"count": 30
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020628581211591758,
"min": 0.013075806988126715,
"max": 0.020725848555836514,
"count": 30
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041257162423183516,
"min": 0.02615161397625343,
"max": 0.05568677033491744,
"count": 30
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05075820485750834,
"min": 0.0226688202470541,
"max": 0.09920784185330073,
"count": 30
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10151640971501669,
"min": 0.0453376404941082,
"max": 0.19841568370660145,
"count": 30
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00027791421736193,
"min": 0.00027791421736193,
"max": 0.0002995349476550175,
"count": 30
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00055582843472386,
"min": 0.00055582843472386,
"max": 0.0008944223118592299,
"count": 30
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.19263807000000002,
"min": 0.19263807000000002,
"max": 0.19984498250000005,
"count": 30
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.38527614000000004,
"min": 0.38527614000000004,
"max": 0.5981407699999999,
"count": 30
},
"Huggy.Policy.Beta.mean": {
"value": 0.004632639692999999,
"min": 0.004632639692999999,
"max": 0.00499226462675,
"count": 30
},
"Huggy.Policy.Beta.sum": {
"value": 0.009265279385999999,
"min": 0.009265279385999999,
"max": 0.014907224423000003,
"count": 30
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1745787703",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745789495"
},
"total": 1791.549257008,
"count": 1,
"self": 0.2252646619999723,
"children": {
"run_training.setup": {
"total": 0.023028409000005468,
"count": 1,
"self": 0.023028409000005468
},
"TrainerController.start_learning": {
"total": 1791.300963937,
"count": 1,
"self": 3.1726059619625175,
"children": {
"TrainerController._reset_env": {
"total": 3.4407720640000434,
"count": 1,
"self": 3.4407720640000434
},
"TrainerController.advance": {
"total": 1784.4950616590377,
"count": 174594,
"self": 3.2724969720823083,
"children": {
"env_step": {
"total": 1418.3635766179968,
"count": 174594,
"self": 1113.5721510399794,
"children": {
"SubprocessEnvManager._take_step": {
"total": 302.8328591840074,
"count": 174594,
"self": 11.866664468959073,
"children": {
"TorchPolicy.evaluate": {
"total": 290.96619471504835,
"count": 167716,
"self": 290.96619471504835
}
}
},
"workers": {
"total": 1.9585663940098925,
"count": 174594,
"self": 0.0,
"children": {
"worker_root": {
"total": 1782.8199790759966,
"count": 174594,
"is_parallel": true,
"self": 874.9795254320414,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008780919999935577,
"count": 1,
"is_parallel": true,
"self": 0.000258051000002979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006200409999905787,
"count": 2,
"is_parallel": true,
"self": 0.0006200409999905787
}
}
},
"UnityEnvironment.step": {
"total": 0.029012960999978077,
"count": 1,
"is_parallel": true,
"self": 0.0003146739999806414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001917349999871476,
"count": 1,
"is_parallel": true,
"self": 0.0001917349999871476
},
"communicator.exchange": {
"total": 0.027823529000045255,
"count": 1,
"is_parallel": true,
"self": 0.027823529000045255
},
"steps_from_proto": {
"total": 0.0006830229999650328,
"count": 1,
"is_parallel": true,
"self": 0.00018168899998727284,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00050133399997776,
"count": 2,
"is_parallel": true,
"self": 0.00050133399997776
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 907.8404536439551,
"count": 174593,
"is_parallel": true,
"self": 27.67055467801947,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 59.36168742794291,
"count": 174593,
"is_parallel": true,
"self": 59.36168742794291
},
"communicator.exchange": {
"total": 757.2572914359514,
"count": 174593,
"is_parallel": true,
"self": 757.2572914359514
},
"steps_from_proto": {
"total": 63.550920102041346,
"count": 174593,
"is_parallel": true,
"self": 22.248767375125738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.30215272691561,
"count": 349186,
"is_parallel": true,
"self": 41.30215272691561
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 362.85898806895847,
"count": 174594,
"self": 4.799817127911581,
"children": {
"process_trajectory": {
"total": 117.10347702504657,
"count": 174594,
"self": 116.53545039804646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5680266270001084,
"count": 3,
"self": 0.5680266270001084
}
}
},
"_update_policy": {
"total": 240.9556939160003,
"count": 73,
"self": 191.51313392600616,
"children": {
"TorchPPOOptimizer.update": {
"total": 49.44255998999415,
"count": 2190,
"self": 49.44255998999415
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.538999640615657e-06,
"count": 1,
"self": 1.538999640615657e-06
},
"TrainerController._save_models": {
"total": 0.19252271300001667,
"count": 1,
"self": 0.002306244000010338,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19021646900000633,
"count": 1,
"self": 0.19021646900000633
}
}
}
}
}
}
}