ppo-Huggy / run_logs /timers.json
Petheron's picture
Huggy
c53ef29 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4019054174423218,
"min": 1.4018851518630981,
"max": 1.428450107574463,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71606.5234375,
"min": 68328.09375,
"max": 77135.2890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.95328719723183,
"min": 83.75257731958763,
"max": 411.0894308943089,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49681.0,
"min": 48744.0,
"max": 50564.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999548.0,
"min": 49937.0,
"max": 1999548.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999548.0,
"min": 49937.0,
"max": 1999548.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3813374042510986,
"min": 0.18447266519069672,
"max": 2.4607625007629395,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1376.4130859375,
"min": 22.505664825439453,
"max": 1407.372314453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7095866439457996,
"min": 1.7286618224910049,
"max": 3.96276530666943,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2144.141080200672,
"min": 210.8967423439026,
"max": 2224.9896555542946,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7095866439457996,
"min": 1.7286618224910049,
"max": 3.96276530666943,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2144.141080200672,
"min": 210.8967423439026,
"max": 2224.9896555542946,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01914897313181427,
"min": 0.012750710148361578,
"max": 0.01982294777505255,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.057446919395442816,
"min": 0.025501420296723157,
"max": 0.057446919395442816,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05340084487365352,
"min": 0.021875076772024233,
"max": 0.06297358522812525,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16020253462096057,
"min": 0.043750153544048466,
"max": 0.18892075568437577,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.524848825083332e-06,
"min": 3.524848825083332e-06,
"max": 0.0002953489515503499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0574546475249996e-05,
"min": 1.0574546475249996e-05,
"max": 0.0008441974686008499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117491666666666,
"min": 0.10117491666666666,
"max": 0.19844965000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30352474999999995,
"min": 0.20748294999999994,
"max": 0.5813991500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.862834166666666e-05,
"min": 6.862834166666666e-05,
"max": 0.004922637535,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020588502499999998,
"min": 0.00020588502499999998,
"max": 0.014071817585,
"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": "1771145233",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1771147796"
},
"total": 2562.9393951519996,
"count": 1,
"self": 0.4853604540003289,
"children": {
"run_training.setup": {
"total": 0.024725381999815,
"count": 1,
"self": 0.024725381999815
},
"TrainerController.start_learning": {
"total": 2562.4293093159995,
"count": 1,
"self": 4.208535119052613,
"children": {
"TrainerController._reset_env": {
"total": 3.4283726429994203,
"count": 1,
"self": 3.4283726429994203
},
"TrainerController.advance": {
"total": 2554.6915495739477,
"count": 231927,
"self": 4.381551371750902,
"children": {
"env_step": {
"total": 2088.278713487185,
"count": 231927,
"self": 1677.243809446084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.29302183300206,
"count": 231927,
"self": 15.345696178106664,
"children": {
"TorchPolicy.evaluate": {
"total": 392.9473256548954,
"count": 222945,
"self": 392.9473256548954
}
}
},
"workers": {
"total": 2.741882208099014,
"count": 231927,
"self": 0.0,
"children": {
"worker_root": {
"total": 2549.844084371948,
"count": 231927,
"is_parallel": true,
"self": 1188.659565455804,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008610350005255896,
"count": 1,
"is_parallel": true,
"self": 0.00026081800024257973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006002170002830098,
"count": 2,
"is_parallel": true,
"self": 0.0006002170002830098
}
}
},
"UnityEnvironment.step": {
"total": 0.03484845899947686,
"count": 1,
"is_parallel": true,
"self": 0.0002514889993108227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018172399995819433,
"count": 1,
"is_parallel": true,
"self": 0.00018172399995819433
},
"communicator.exchange": {
"total": 0.033928359000128694,
"count": 1,
"is_parallel": true,
"self": 0.033928359000128694
},
"steps_from_proto": {
"total": 0.0004868870000791503,
"count": 1,
"is_parallel": true,
"self": 0.00016334300016751513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003235439999116352,
"count": 2,
"is_parallel": true,
"self": 0.0003235439999116352
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1361.184518916144,
"count": 231926,
"is_parallel": true,
"self": 38.459841056129335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.98897966289132,
"count": 231926,
"is_parallel": true,
"self": 81.98897966289132
},
"communicator.exchange": {
"total": 1150.6023707671102,
"count": 231926,
"is_parallel": true,
"self": 1150.6023707671102
},
"steps_from_proto": {
"total": 90.1333274300132,
"count": 231926,
"is_parallel": true,
"self": 32.07197640926188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.06135102075132,
"count": 463852,
"is_parallel": true,
"self": 58.06135102075132
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 462.0312847150117,
"count": 231927,
"self": 6.524468056101796,
"children": {
"process_trajectory": {
"total": 152.47543042791312,
"count": 231927,
"self": 151.3069268779118,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1685035500013328,
"count": 10,
"self": 1.1685035500013328
}
}
},
"_update_policy": {
"total": 303.03138623099676,
"count": 97,
"self": 239.9371653769913,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.09422085400547,
"count": 2910,
"self": 63.09422085400547
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.799997885944322e-07,
"count": 1,
"self": 8.799997885944322e-07
},
"TrainerController._save_models": {
"total": 0.10085109999999986,
"count": 1,
"self": 0.0016713459999664337,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09917975400003343,
"count": 1,
"self": 0.09917975400003343
}
}
}
}
}
}
}