ppo-Huggy / run_logs /timers.json
Eric0804's picture
Huggy
01b2647 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053151607513428,
"min": 1.4053151607513428,
"max": 1.4284024238586426,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70085.875,
"min": 68889.078125,
"max": 77907.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.0374149659864,
"min": 78.30385852090032,
"max": 407.5365853658537,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49414.0,
"min": 48705.0,
"max": 50174.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49854.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49854.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3933866024017334,
"min": 0.12473393231630325,
"max": 2.4674177169799805,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1407.311279296875,
"min": 15.21753978729248,
"max": 1505.124755859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7034376608271176,
"min": 1.7499509082465876,
"max": 3.9466356339024715,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2177.621344566345,
"min": 213.49401080608368,
"max": 2407.4477366805077,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7034376608271176,
"min": 1.7499509082465876,
"max": 3.9466356339024715,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2177.621344566345,
"min": 213.49401080608368,
"max": 2407.4477366805077,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018057260239988358,
"min": 0.013271799940654697,
"max": 0.020116478542331607,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054171780719965076,
"min": 0.026543599881309395,
"max": 0.05696282015948479,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05741053910719024,
"min": 0.021067791214833657,
"max": 0.06324729124704997,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17223161732157072,
"min": 0.04213558242966731,
"max": 0.18974187374114992,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.634398788566657e-06,
"min": 3.634398788566657e-06,
"max": 0.0002953647015451,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0903196365699971e-05,
"min": 1.0903196365699971e-05,
"max": 0.0008439385686871497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121143333333334,
"min": 0.10121143333333334,
"max": 0.19845489999999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036343,
"min": 0.2075575,
"max": 0.58131285,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.045052333333318e-05,
"min": 7.045052333333318e-05,
"max": 0.00492289951,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021135156999999951,
"min": 0.00021135156999999951,
"max": 0.014067511215000002,
"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": "1745323410",
"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": "1745325785"
},
"total": 2375.422288866,
"count": 1,
"self": 0.4384454940004616,
"children": {
"run_training.setup": {
"total": 0.022225964000028853,
"count": 1,
"self": 0.022225964000028853
},
"TrainerController.start_learning": {
"total": 2374.9616174079997,
"count": 1,
"self": 4.062005980988033,
"children": {
"TrainerController._reset_env": {
"total": 3.0035516890000054,
"count": 1,
"self": 3.0035516890000054
},
"TrainerController.advance": {
"total": 2367.7899227620123,
"count": 232406,
"self": 4.235866470992278,
"children": {
"env_step": {
"total": 1874.4739335810482,
"count": 232406,
"self": 1462.7395845740232,
"children": {
"SubprocessEnvManager._take_step": {
"total": 409.15645270205226,
"count": 232406,
"self": 15.757856718067046,
"children": {
"TorchPolicy.evaluate": {
"total": 393.3985959839852,
"count": 222896,
"self": 393.3985959839852
}
}
},
"workers": {
"total": 2.5778963049727395,
"count": 232406,
"self": 0.0,
"children": {
"worker_root": {
"total": 2368.06675352203,
"count": 232406,
"is_parallel": true,
"self": 1176.4580115240851,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022939199999996163,
"count": 1,
"is_parallel": true,
"self": 0.00047752799997624606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018163920000233702,
"count": 2,
"is_parallel": true,
"self": 0.0018163920000233702
}
}
},
"UnityEnvironment.step": {
"total": 0.028191661999983353,
"count": 1,
"is_parallel": true,
"self": 0.00030579300005229015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020518100001254425,
"count": 1,
"is_parallel": true,
"self": 0.00020518100001254425
},
"communicator.exchange": {
"total": 0.027000395999948523,
"count": 1,
"is_parallel": true,
"self": 0.027000395999948523
},
"steps_from_proto": {
"total": 0.0006802919999699952,
"count": 1,
"is_parallel": true,
"self": 0.00019360699997150732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004866849999984879,
"count": 2,
"is_parallel": true,
"self": 0.0004866849999984879
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1191.608741997945,
"count": 232405,
"is_parallel": true,
"self": 36.67173982791451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.74249356796099,
"count": 232405,
"is_parallel": true,
"self": 79.74249356796099
},
"communicator.exchange": {
"total": 990.9999960410562,
"count": 232405,
"is_parallel": true,
"self": 990.9999960410562
},
"steps_from_proto": {
"total": 84.19451256101314,
"count": 232405,
"is_parallel": true,
"self": 29.722015812850373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.47249674816277,
"count": 464810,
"is_parallel": true,
"self": 54.47249674816277
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.0801227099718,
"count": 232406,
"self": 6.269238895991123,
"children": {
"process_trajectory": {
"total": 158.47727551198238,
"count": 232406,
"self": 157.18220665798265,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2950688539997373,
"count": 10,
"self": 1.2950688539997373
}
}
},
"_update_policy": {
"total": 324.3336083019983,
"count": 97,
"self": 257.3064613709993,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.02714693099904,
"count": 2910,
"self": 67.02714693099904
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.499996511091013e-07,
"count": 1,
"self": 8.499996511091013e-07
},
"TrainerController._save_models": {
"total": 0.10613612599991029,
"count": 1,
"self": 0.001571049000176572,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10456507699973372,
"count": 1,
"self": 0.10456507699973372
}
}
}
}
}
}
}