ppo-Huggy / run_logs /timers.json
fivedoctors's picture
Huggy
f6f8399 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016820192337036,
"min": 1.4016820192337036,
"max": 1.4028435945510864,
"count": 9
},
"Huggy.Policy.Entropy.sum": {
"value": 68859.03125,
"min": 681.781982421875,
"max": 71557.4140625,
"count": 9
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.22830188679245,
"min": 25.5,
"max": 93.22830188679245,
"count": 9
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49411.0,
"min": 51.0,
"max": 50096.0,
"count": 9
},
"Huggy.Step.mean": {
"value": 1999922.0,
"min": 1599981.0,
"max": 1999922.0,
"count": 9
},
"Huggy.Step.sum": {
"value": 1999922.0,
"min": 1599981.0,
"max": 1999922.0,
"count": 9
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4125115871429443,
"min": 1.9608110189437866,
"max": 2.4790518283843994,
"count": 9
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1278.631103515625,
"min": 1.9608110189437866,
"max": 1750.259521484375,
"count": 9
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.65817711353302,
"min": 2.110610008239746,
"max": 3.866444780385538,
"count": 9
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1938.8338701725006,
"min": 2.110610008239746,
"max": 2703.755170941353,
"count": 9
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.65817711353302,
"min": 2.110610008239746,
"max": 3.866444780385538,
"count": 9
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1938.8338701725006,
"min": 2.110610008239746,
"max": 2703.755170941353,
"count": 9
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 9
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 9
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01459927267084519,
"min": 0.01459927267084519,
"max": 0.01836292537433716,
"count": 8
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02919854534169038,
"min": 0.02919854534169038,
"max": 0.05029498783308857,
"count": 8
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047823805920779706,
"min": 0.047823805920779706,
"max": 0.06452960067739089,
"count": 8
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09564761184155941,
"min": 0.09564761184155941,
"max": 0.18660750674704712,
"count": 8
},
"Huggy.Policy.LearningRate.mean": {
"value": 2.920599026499998e-06,
"min": 2.920599026499998e-06,
"max": 5.5391331536250004e-05,
"count": 8
},
"Huggy.Policy.LearningRate.sum": {
"value": 5.841198052999996e-06,
"min": 5.841198052999996e-06,
"max": 0.00012461110846305001,
"count": 8
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10097350000000002,
"min": 0.10097350000000002,
"max": 0.11846375000000002,
"count": 8
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20194700000000004,
"min": 0.20194700000000004,
"max": 0.34153695,
"count": 8
},
"Huggy.Policy.Beta.mean": {
"value": 5.857764999999996e-05,
"min": 5.857764999999996e-05,
"max": 0.0009313411250000002,
"count": 8
},
"Huggy.Policy.Beta.sum": {
"value": 0.00011715529999999993,
"min": 0.00011715529999999993,
"max": 0.002102693805,
"count": 8
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1746086870",
"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 --resume",
"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": "1746087380"
},
"total": 509.8871500150003,
"count": 1,
"self": 0.4306175460005761,
"children": {
"run_training.setup": {
"total": 0.020697079000001395,
"count": 1,
"self": 0.020697079000001395
},
"TrainerController.start_learning": {
"total": 509.43583538999974,
"count": 1,
"self": 0.9382676060090489,
"children": {
"TrainerController._reset_env": {
"total": 2.1529421169998386,
"count": 1,
"self": 2.1529421169998386
},
"TrainerController.advance": {
"total": 506.2098249049909,
"count": 47234,
"self": 1.0293801460256873,
"children": {
"env_step": {
"total": 407.4858295830254,
"count": 47234,
"self": 321.616286179702,
"children": {
"SubprocessEnvManager._take_step": {
"total": 85.31888361716074,
"count": 47234,
"self": 3.154644749083218,
"children": {
"TorchPolicy.evaluate": {
"total": 82.16423886807752,
"count": 44808,
"self": 82.16423886807752
}
}
},
"workers": {
"total": 0.5506597861626688,
"count": 47234,
"self": 0.0,
"children": {
"worker_root": {
"total": 507.6673578059108,
"count": 47234,
"is_parallel": true,
"self": 245.02823868483665,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000888960999873234,
"count": 1,
"is_parallel": true,
"self": 0.0002946279996649537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005943330002082803,
"count": 2,
"is_parallel": true,
"self": 0.0005943330002082803
}
}
},
"UnityEnvironment.step": {
"total": 0.0314977920002093,
"count": 1,
"is_parallel": true,
"self": 0.00026008400027421885,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020973399978174712,
"count": 1,
"is_parallel": true,
"self": 0.00020973399978174712
},
"communicator.exchange": {
"total": 0.028549392000059015,
"count": 1,
"is_parallel": true,
"self": 0.028549392000059015
},
"steps_from_proto": {
"total": 0.0024785820000943204,
"count": 1,
"is_parallel": true,
"self": 0.00017231299989362014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023062690002007002,
"count": 2,
"is_parallel": true,
"self": 0.0023062690002007002
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 262.63911912107415,
"count": 47233,
"is_parallel": true,
"self": 7.621151651121181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 16.8247537749985,
"count": 47233,
"is_parallel": true,
"self": 16.8247537749985
},
"communicator.exchange": {
"total": 220.13541845301006,
"count": 47233,
"is_parallel": true,
"self": 220.13541845301006
},
"steps_from_proto": {
"total": 18.057795241944405,
"count": 47233,
"is_parallel": true,
"self": 6.733866285066142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.323928956878262,
"count": 94466,
"is_parallel": true,
"self": 11.323928956878262
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 97.69461517593982,
"count": 47234,
"self": 1.3324857748684735,
"children": {
"process_trajectory": {
"total": 36.77935617407093,
"count": 47234,
"self": 36.37358881807177,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4057673559991599,
"count": 3,
"self": 0.4057673559991599
}
}
},
"_update_policy": {
"total": 59.582773227000416,
"count": 19,
"self": 47.07002094400514,
"children": {
"TorchPPOOptimizer.update": {
"total": 12.51275228299528,
"count": 570,
"self": 12.51275228299528
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.530003808322363e-07,
"count": 1,
"self": 9.530003808322363e-07
},
"TrainerController._save_models": {
"total": 0.1347998089995599,
"count": 1,
"self": 0.0017559669995534932,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1330438420000064,
"count": 1,
"self": 0.1330438420000064
}
}
}
}
}
}
}