ppo-Huggy / run_logs /timers.json
adrian-nf's picture
Huggy
868681e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074493646621704,
"min": 1.4074493646621704,
"max": 1.4331814050674438,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70417.5078125,
"min": 69365.90625,
"max": 78496.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.63829787234043,
"min": 83.42567567567568,
"max": 382.74242424242425,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49428.0,
"min": 48703.0,
"max": 50522.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999935.0,
"min": 49905.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999935.0,
"min": 49905.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.423020601272583,
"min": 0.0659584328532219,
"max": 2.461012125015259,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1366.5836181640625,
"min": 8.640554428100586,
"max": 1428.6749267578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.729025491374604,
"min": 1.819267203107135,
"max": 4.037371102514302,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2103.170377135277,
"min": 238.32400360703468,
"max": 2224.5545502901077,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.729025491374604,
"min": 1.819267203107135,
"max": 4.037371102514302,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2103.170377135277,
"min": 238.32400360703468,
"max": 2224.5545502901077,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015037376608314742,
"min": 0.012806674849950165,
"max": 0.020581158230197613,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045112129824944225,
"min": 0.02561334969990033,
"max": 0.05633661053143442,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05365632408195071,
"min": 0.021318454978366694,
"max": 0.05775997396558523,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16096897224585213,
"min": 0.04263690995673339,
"max": 0.16846622427304586,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6228987924000045e-06,
"min": 3.6228987924000045e-06,
"max": 0.00029532075155974994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0868696377200013e-05,
"min": 1.0868696377200013e-05,
"max": 0.0008436183187938999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012076,
"min": 0.1012076,
"max": 0.19844025,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362279999999997,
"min": 0.20759554999999996,
"max": 0.5812061,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.025924000000009e-05,
"min": 7.025924000000009e-05,
"max": 0.004922168474999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021077772000000026,
"min": 0.00021077772000000026,
"max": 0.014062184390000001,
"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": "1733309685",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733312385"
},
"total": 2699.996970706,
"count": 1,
"self": 0.8032884750000449,
"children": {
"run_training.setup": {
"total": 0.05795254899999236,
"count": 1,
"self": 0.05795254899999236
},
"TrainerController.start_learning": {
"total": 2699.1357296819997,
"count": 1,
"self": 5.253925451913801,
"children": {
"TrainerController._reset_env": {
"total": 5.888861822000081,
"count": 1,
"self": 5.888861822000081
},
"TrainerController.advance": {
"total": 2687.804510855086,
"count": 232240,
"self": 5.31708289714561,
"children": {
"env_step": {
"total": 2142.665687043081,
"count": 232240,
"self": 1681.9030373930052,
"children": {
"SubprocessEnvManager._take_step": {
"total": 457.4434702200675,
"count": 232240,
"self": 17.31253885711476,
"children": {
"TorchPolicy.evaluate": {
"total": 440.13093136295277,
"count": 222938,
"self": 440.13093136295277
}
}
},
"workers": {
"total": 3.3191794300083757,
"count": 232240,
"self": 0.0,
"children": {
"worker_root": {
"total": 2690.5827064270443,
"count": 232240,
"is_parallel": true,
"self": 1328.7642423370069,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009383359999901586,
"count": 1,
"is_parallel": true,
"self": 0.0002624489998197532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006758870001704054,
"count": 2,
"is_parallel": true,
"self": 0.0006758870001704054
}
}
},
"UnityEnvironment.step": {
"total": 0.029821973000025537,
"count": 1,
"is_parallel": true,
"self": 0.000424121000037303,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019497799996770482,
"count": 1,
"is_parallel": true,
"self": 0.00019497799996770482
},
"communicator.exchange": {
"total": 0.028344369000024017,
"count": 1,
"is_parallel": true,
"self": 0.028344369000024017
},
"steps_from_proto": {
"total": 0.0008585049999965122,
"count": 1,
"is_parallel": true,
"self": 0.00022247299989430758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006360320001022046,
"count": 2,
"is_parallel": true,
"self": 0.0006360320001022046
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1361.8184640900374,
"count": 232239,
"is_parallel": true,
"self": 40.63595703789201,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.83964407804865,
"count": 232239,
"is_parallel": true,
"self": 86.83964407804865
},
"communicator.exchange": {
"total": 1135.9599750211105,
"count": 232239,
"is_parallel": true,
"self": 1135.9599750211105
},
"steps_from_proto": {
"total": 98.38288795298638,
"count": 232239,
"is_parallel": true,
"self": 36.30391130104897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.07897665193741,
"count": 464478,
"is_parallel": true,
"self": 62.07897665193741
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 539.8217409148591,
"count": 232240,
"self": 7.699763515892528,
"children": {
"process_trajectory": {
"total": 182.88306569396684,
"count": 232240,
"self": 181.01850959396722,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8645560999996178,
"count": 10,
"self": 1.8645560999996178
}
}
},
"_update_policy": {
"total": 349.23891170499974,
"count": 97,
"self": 281.0717571340035,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.16715457099622,
"count": 2910,
"self": 68.16715457099622
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.273999714612728e-06,
"count": 1,
"self": 1.273999714612728e-06
},
"TrainerController._save_models": {
"total": 0.18843027900038578,
"count": 1,
"self": 0.002903255000092031,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18552702400029375,
"count": 1,
"self": 0.18552702400029375
}
}
}
}
}
}
}