ppo-Huggy / run_logs /timers.json
csaez's picture
Huggy
67f23e8 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4005793333053589,
"min": 1.4005793333053589,
"max": 1.427816390991211,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70629.8125,
"min": 67898.625,
"max": 78846.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 135.07837837837837,
"min": 109.94690265486726,
"max": 437.7543859649123,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49979.0,
"min": 48985.0,
"max": 50149.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999656.0,
"min": 49786.0,
"max": 1999656.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999656.0,
"min": 49786.0,
"max": 1999656.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2490735054016113,
"min": 0.024270731955766678,
"max": 2.308159828186035,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 832.1572265625,
"min": 2.7425928115844727,
"max": 1039.273193359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4442734650663427,
"min": 1.977668096006444,
"max": 3.7936922029223084,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1274.3811820745468,
"min": 223.47649484872818,
"max": 1608.5254940390587,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4442734650663427,
"min": 1.977668096006444,
"max": 3.7936922029223084,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1274.3811820745468,
"min": 223.47649484872818,
"max": 1608.5254940390587,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01400848678846766,
"min": 0.01400848678846766,
"max": 0.019606428475041564,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02801697357693532,
"min": 0.02801697357693532,
"max": 0.058320250329173484,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03866617102175951,
"min": 0.021715513709932563,
"max": 0.06589573547244072,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07733234204351902,
"min": 0.043431027419865126,
"max": 0.19768720641732215,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.322423559224998e-06,
"min": 4.322423559224998e-06,
"max": 0.00029533357655547497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.644847118449996e-06,
"min": 8.644847118449996e-06,
"max": 0.0008441142186285999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101440775,
"min": 0.101440775,
"max": 0.19844452499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20288155,
"min": 0.20288155,
"max": 0.5813714000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.189467249999998e-05,
"min": 8.189467249999998e-05,
"max": 0.0049223817975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016378934499999996,
"min": 0.00016378934499999996,
"max": 0.014070432859999999,
"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": "1745003084",
"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": "1745005468"
},
"total": 2384.0578510259998,
"count": 1,
"self": 0.4365909319999446,
"children": {
"run_training.setup": {
"total": 0.022913475999985167,
"count": 1,
"self": 0.022913475999985167
},
"TrainerController.start_learning": {
"total": 2383.598346618,
"count": 1,
"self": 4.335602932972961,
"children": {
"TrainerController._reset_env": {
"total": 3.1418437209999865,
"count": 1,
"self": 3.1418437209999865
},
"TrainerController.advance": {
"total": 2376.013810227027,
"count": 230344,
"self": 4.175884482973743,
"children": {
"env_step": {
"total": 1900.1624412740036,
"count": 230344,
"self": 1485.4826714610401,
"children": {
"SubprocessEnvManager._take_step": {
"total": 412.0421363490466,
"count": 230344,
"self": 15.272833356124238,
"children": {
"TorchPolicy.evaluate": {
"total": 396.76930299292235,
"count": 223082,
"self": 396.76930299292235
}
}
},
"workers": {
"total": 2.637633463916927,
"count": 230344,
"self": 0.0,
"children": {
"worker_root": {
"total": 2376.6201334379607,
"count": 230344,
"is_parallel": true,
"self": 1161.6944352179576,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009885860000622415,
"count": 1,
"is_parallel": true,
"self": 0.0003581730001087635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000630412999953478,
"count": 2,
"is_parallel": true,
"self": 0.000630412999953478
}
}
},
"UnityEnvironment.step": {
"total": 0.030703162000008888,
"count": 1,
"is_parallel": true,
"self": 0.00032481500011272146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001864639999666906,
"count": 1,
"is_parallel": true,
"self": 0.0001864639999666906
},
"communicator.exchange": {
"total": 0.029537104999917574,
"count": 1,
"is_parallel": true,
"self": 0.029537104999917574
},
"steps_from_proto": {
"total": 0.0006547780000119019,
"count": 1,
"is_parallel": true,
"self": 0.00017726900000525347,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004775090000066484,
"count": 2,
"is_parallel": true,
"self": 0.0004775090000066484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.9256982200031,
"count": 230343,
"is_parallel": true,
"self": 36.59719654311016,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.73220178700592,
"count": 230343,
"is_parallel": true,
"self": 79.73220178700592
},
"communicator.exchange": {
"total": 1014.9834362269751,
"count": 230343,
"is_parallel": true,
"self": 1014.9834362269751
},
"steps_from_proto": {
"total": 83.6128636629121,
"count": 230343,
"is_parallel": true,
"self": 29.158771776083313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.45409188682879,
"count": 460686,
"is_parallel": true,
"self": 54.45409188682879
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 471.6754844700498,
"count": 230344,
"self": 6.625403617944244,
"children": {
"process_trajectory": {
"total": 147.75614752010188,
"count": 230344,
"self": 146.5425483641019,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2135991559999866,
"count": 10,
"self": 1.2135991559999866
}
}
},
"_update_policy": {
"total": 317.2939333320037,
"count": 96,
"self": 251.19858276700495,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.09535056499874,
"count": 2880,
"self": 66.09535056499874
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.499999578110874e-07,
"count": 1,
"self": 9.499999578110874e-07
},
"TrainerController._save_models": {
"total": 0.10708878700006608,
"count": 1,
"self": 0.0016228810004577099,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10546590599960837,
"count": 1,
"self": 0.10546590599960837
}
}
}
}
}
}
}