ppo-Huggy / run_logs /timers.json
debisoft's picture
Huggy
db69cc8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4026219844818115,
"min": 1.4026219844818115,
"max": 1.4275705814361572,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69271.2890625,
"min": 67360.78125,
"max": 79426.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.18859649122807,
"min": 92.76547842401501,
"max": 405.60483870967744,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48878.0,
"min": 48878.0,
"max": 50295.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49775.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49775.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.366234064102173,
"min": 0.04946218058466911,
"max": 2.408170700073242,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1079.002685546875,
"min": 6.083847999572754,
"max": 1252.248779296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6887146673704447,
"min": 1.9620467298399142,
"max": 3.7988408079514135,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1682.0538883209229,
"min": 241.33174777030945,
"max": 1975.397220134735,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6887146673704447,
"min": 1.9620467298399142,
"max": 3.7988408079514135,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1682.0538883209229,
"min": 241.33174777030945,
"max": 1975.397220134735,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01738263023435138,
"min": 0.013502678184643931,
"max": 0.01936969625821803,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03476526046870276,
"min": 0.027005356369287862,
"max": 0.053561418623818705,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0438807745774587,
"min": 0.020268007492025696,
"max": 0.059950592927634716,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0877615491549174,
"min": 0.04053601498405139,
"max": 0.17407736058036485,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.539473486874995e-06,
"min": 4.539473486874995e-06,
"max": 0.00029531482656172496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.07894697374999e-06,
"min": 9.07894697374999e-06,
"max": 0.0008438025187324998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151312499999998,
"min": 0.10151312499999998,
"max": 0.198438275,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20302624999999996,
"min": 0.20302624999999996,
"max": 0.5812675,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.550493749999997e-05,
"min": 8.550493749999997e-05,
"max": 0.004922069922500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017100987499999993,
"min": 0.00017100987499999993,
"max": 0.014065248250000002,
"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": "1754403376",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1754405840"
},
"total": 2464.037864724,
"count": 1,
"self": 0.7535459989999254,
"children": {
"run_training.setup": {
"total": 0.0218739160000041,
"count": 1,
"self": 0.0218739160000041
},
"TrainerController.start_learning": {
"total": 2463.262444809,
"count": 1,
"self": 4.184024498947565,
"children": {
"TrainerController._reset_env": {
"total": 3.075771245999988,
"count": 1,
"self": 3.075771245999988
},
"TrainerController.advance": {
"total": 2455.824838468053,
"count": 231324,
"self": 4.2575489381688385,
"children": {
"env_step": {
"total": 1969.5836163699896,
"count": 231324,
"self": 1563.3995222470971,
"children": {
"SubprocessEnvManager._take_step": {
"total": 403.5405353689046,
"count": 231324,
"self": 14.807456292786185,
"children": {
"TorchPolicy.evaluate": {
"total": 388.73307907611843,
"count": 222955,
"self": 388.73307907611843
}
}
},
"workers": {
"total": 2.6435587539877474,
"count": 231324,
"self": 0.0,
"children": {
"worker_root": {
"total": 2455.703193287035,
"count": 231324,
"is_parallel": true,
"self": 1174.8665190780791,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008465639999712948,
"count": 1,
"is_parallel": true,
"self": 0.0002604919999953381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005860719999759567,
"count": 2,
"is_parallel": true,
"self": 0.0005860719999759567
}
}
},
"UnityEnvironment.step": {
"total": 0.028884225000012975,
"count": 1,
"is_parallel": true,
"self": 0.00026212099999156635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001934219999952802,
"count": 1,
"is_parallel": true,
"self": 0.0001934219999952802
},
"communicator.exchange": {
"total": 0.027753673999995954,
"count": 1,
"is_parallel": true,
"self": 0.027753673999995954
},
"steps_from_proto": {
"total": 0.000675008000030175,
"count": 1,
"is_parallel": true,
"self": 0.0001850130000207173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004899950000094577,
"count": 2,
"is_parallel": true,
"self": 0.0004899950000094577
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1280.8366742089559,
"count": 231323,
"is_parallel": true,
"self": 36.68930022384416,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.43937600407014,
"count": 231323,
"is_parallel": true,
"self": 83.43937600407014
},
"communicator.exchange": {
"total": 1072.5277090679897,
"count": 231323,
"is_parallel": true,
"self": 1072.5277090679897
},
"steps_from_proto": {
"total": 88.18028891305181,
"count": 231323,
"is_parallel": true,
"self": 32.92818111403932,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.25210779901249,
"count": 462646,
"is_parallel": true,
"self": 55.25210779901249
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.9836731598943,
"count": 231324,
"self": 6.358174266881349,
"children": {
"process_trajectory": {
"total": 154.3683418950137,
"count": 231324,
"self": 153.11054124801376,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2578006469999536,
"count": 10,
"self": 1.2578006469999536
}
}
},
"_update_policy": {
"total": 321.25715699799923,
"count": 96,
"self": 259.78032047299314,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.47683652500609,
"count": 2880,
"self": 61.47683652500609
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.25599990496994e-06,
"count": 1,
"self": 1.25599990496994e-06
},
"TrainerController._save_models": {
"total": 0.17780933999983972,
"count": 1,
"self": 0.002306589999989228,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1755027499998505,
"count": 1,
"self": 0.1755027499998505
}
}
}
}
}
}
}