ppo-Huggy / run_logs /timers.json
takahashi24's picture
Huggy
dcb3091 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402422547340393,
"min": 1.402422547340393,
"max": 1.427962064743042,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71494.1015625,
"min": 69109.2734375,
"max": 76786.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.77327327327328,
"min": 73.91467065868264,
"max": 402.6209677419355,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49799.0,
"min": 48734.0,
"max": 50094.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999740.0,
"min": 49407.0,
"max": 1999740.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999740.0,
"min": 49407.0,
"max": 1999740.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4622457027435303,
"min": 0.07411858439445496,
"max": 2.5456185340881348,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1639.855712890625,
"min": 9.116585731506348,
"max": 1657.021240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9018187477244988,
"min": 1.8962708527479715,
"max": 4.086972341187323,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2598.611285984516,
"min": 233.2413148880005,
"max": 2635.3049540519714,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9018187477244988,
"min": 1.8962708527479715,
"max": 4.086972341187323,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2598.611285984516,
"min": 233.2413148880005,
"max": 2635.3049540519714,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016078741226616938,
"min": 0.013233396099531093,
"max": 0.019153083080406457,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04823622367985081,
"min": 0.026466792199062186,
"max": 0.0545927464098592,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06033064532611104,
"min": 0.021238853875547647,
"max": 0.06033064532611104,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18099193597833313,
"min": 0.042477707751095294,
"max": 0.18099193597833313,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8708987097333306e-06,
"min": 3.8708987097333306e-06,
"max": 0.0002953299765566751,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1612696129199993e-05,
"min": 1.1612696129199993e-05,
"max": 0.00084415396861535,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129026666666668,
"min": 0.10129026666666668,
"max": 0.198443325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30387080000000005,
"min": 0.20772725000000003,
"max": 0.5813846500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.438430666666661e-05,
"min": 7.438430666666661e-05,
"max": 0.0049223219175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022315291999999983,
"min": 0.00022315291999999983,
"max": 0.014071094034999999,
"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": "1738761697",
"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": "1738764184"
},
"total": 2486.4911752630005,
"count": 1,
"self": 0.44616219400086266,
"children": {
"run_training.setup": {
"total": 0.022620826999855126,
"count": 1,
"self": 0.022620826999855126
},
"TrainerController.start_learning": {
"total": 2486.022392242,
"count": 1,
"self": 4.482850471010352,
"children": {
"TrainerController._reset_env": {
"total": 2.994015388999969,
"count": 1,
"self": 2.994015388999969
},
"TrainerController.advance": {
"total": 2478.43353348599,
"count": 233245,
"self": 4.657247546226699,
"children": {
"env_step": {
"total": 1945.7603584380004,
"count": 233245,
"self": 1527.0316337091067,
"children": {
"SubprocessEnvManager._take_step": {
"total": 416.03446407792717,
"count": 233245,
"self": 15.67533431987772,
"children": {
"TorchPolicy.evaluate": {
"total": 400.35912975804945,
"count": 222968,
"self": 400.35912975804945
}
}
},
"workers": {
"total": 2.6942606509664984,
"count": 233245,
"self": 0.0,
"children": {
"worker_root": {
"total": 2478.5334809980427,
"count": 233245,
"is_parallel": true,
"self": 1231.3112673230523,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001082054999869797,
"count": 1,
"is_parallel": true,
"self": 0.00039309899989348196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006889559999763151,
"count": 2,
"is_parallel": true,
"self": 0.0006889559999763151
}
}
},
"UnityEnvironment.step": {
"total": 0.0293963840001652,
"count": 1,
"is_parallel": true,
"self": 0.0003091539999786619,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021530100002564723,
"count": 1,
"is_parallel": true,
"self": 0.00021530100002564723
},
"communicator.exchange": {
"total": 0.028161510000018097,
"count": 1,
"is_parallel": true,
"self": 0.028161510000018097
},
"steps_from_proto": {
"total": 0.0007104190001427924,
"count": 1,
"is_parallel": true,
"self": 0.00020023000024593784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005101889998968545,
"count": 2,
"is_parallel": true,
"self": 0.0005101889998968545
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1247.2222136749904,
"count": 233244,
"is_parallel": true,
"self": 36.41083321003862,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.05408520096103,
"count": 233244,
"is_parallel": true,
"self": 81.05408520096103
},
"communicator.exchange": {
"total": 1041.9304677890696,
"count": 233244,
"is_parallel": true,
"self": 1041.9304677890696
},
"steps_from_proto": {
"total": 87.82682747492117,
"count": 233244,
"is_parallel": true,
"self": 32.46792680563544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.35890066928573,
"count": 466488,
"is_parallel": true,
"self": 55.35890066928573
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.0159275017634,
"count": 233245,
"self": 6.3169773848421755,
"children": {
"process_trajectory": {
"total": 169.74119460392103,
"count": 233245,
"self": 168.3985007589206,
"children": {
"RLTrainer._checkpoint": {
"total": 1.34269384500044,
"count": 10,
"self": 1.34269384500044
}
}
},
"_update_policy": {
"total": 351.95775551300017,
"count": 97,
"self": 283.23346065399096,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.7242948590092,
"count": 2910,
"self": 68.7242948590092
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.380000847158954e-07,
"count": 1,
"self": 9.380000847158954e-07
},
"TrainerController._save_models": {
"total": 0.1119919579996349,
"count": 1,
"self": 0.00187440799891192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11011755000072299,
"count": 1,
"self": 0.11011755000072299
}
}
}
}
}
}
}