ppo-Huggy / run_logs /timers.json
lordpepe's picture
Huggy
d06b2db
raw
history blame
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3996158838272095,
"min": 1.3996158838272095,
"max": 1.426277756690979,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71822.6875,
"min": 66491.765625,
"max": 80617.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.83658969804618,
"min": 80.2512077294686,
"max": 404.9596774193548,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49452.0,
"min": 48999.0,
"max": 50215.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999900.0,
"min": 49719.0,
"max": 1999900.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999900.0,
"min": 49719.0,
"max": 1999900.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.425318479537964,
"min": 0.08312324434518814,
"max": 2.4726901054382324,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1365.454345703125,
"min": 10.224159240722656,
"max": 1478.7010498046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.660835384052134,
"min": 1.8176607574389232,
"max": 3.9393293428336023,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2061.0503212213516,
"min": 223.57227316498756,
"max": 2299.456688940525,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.660835384052134,
"min": 1.8176607574389232,
"max": 3.9393293428336023,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2061.0503212213516,
"min": 223.57227316498756,
"max": 2299.456688940525,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016484877169649633,
"min": 0.012825024234189186,
"max": 0.020333287958379107,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0494546315089489,
"min": 0.025650048468378372,
"max": 0.060999863875137325,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05185307231214312,
"min": 0.022530130131377113,
"max": 0.06412655655294656,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15555921693642935,
"min": 0.04573965525875489,
"max": 0.19077840074896812,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5078988307333286e-06,
"min": 3.5078988307333286e-06,
"max": 0.00029531895156034997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0523696492199986e-05,
"min": 1.0523696492199986e-05,
"max": 0.0008441916186028001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116926666666666,
"min": 0.10116926666666666,
"max": 0.19843964999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035078,
"min": 0.20750640000000004,
"max": 0.5813972,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.834640666666658e-05,
"min": 6.834640666666658e-05,
"max": 0.004922138535000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020503921999999973,
"min": 0.00020503921999999973,
"max": 0.014071720279999995,
"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": "1688071363",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688074355"
},
"total": 2991.8694520719996,
"count": 1,
"self": 0.6154541379996772,
"children": {
"run_training.setup": {
"total": 0.0514875920000577,
"count": 1,
"self": 0.0514875920000577
},
"TrainerController.start_learning": {
"total": 2991.202510342,
"count": 1,
"self": 6.233742491253452,
"children": {
"TrainerController._reset_env": {
"total": 4.720721544999833,
"count": 1,
"self": 4.720721544999833
},
"TrainerController.advance": {
"total": 2980.1114401087466,
"count": 232357,
"self": 5.903926097535532,
"children": {
"env_step": {
"total": 2323.732016913306,
"count": 232357,
"self": 1961.1084250132365,
"children": {
"SubprocessEnvManager._take_step": {
"total": 358.8364611481679,
"count": 232357,
"self": 20.839891150314998,
"children": {
"TorchPolicy.evaluate": {
"total": 337.99656999785293,
"count": 223028,
"self": 337.99656999785293
}
}
},
"workers": {
"total": 3.7871307519014863,
"count": 232357,
"self": 0.0,
"children": {
"worker_root": {
"total": 2981.457218087084,
"count": 232357,
"is_parallel": true,
"self": 1382.6782622630274,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001002003999929002,
"count": 1,
"is_parallel": true,
"self": 0.0002458970000134286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007561069999155734,
"count": 2,
"is_parallel": true,
"self": 0.0007561069999155734
}
}
},
"UnityEnvironment.step": {
"total": 0.032423116000018126,
"count": 1,
"is_parallel": true,
"self": 0.000316330000259768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002595319999727508,
"count": 1,
"is_parallel": true,
"self": 0.0002595319999727508
},
"communicator.exchange": {
"total": 0.031018410999877233,
"count": 1,
"is_parallel": true,
"self": 0.031018410999877233
},
"steps_from_proto": {
"total": 0.0008288429999083746,
"count": 1,
"is_parallel": true,
"self": 0.00021392400003605871,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006149189998723159,
"count": 2,
"is_parallel": true,
"self": 0.0006149189998723159
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1598.7789558240568,
"count": 232356,
"is_parallel": true,
"self": 46.87213563424075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.06735940789326,
"count": 232356,
"is_parallel": true,
"self": 93.06735940789326
},
"communicator.exchange": {
"total": 1342.0060190348315,
"count": 232356,
"is_parallel": true,
"self": 1342.0060190348315
},
"steps_from_proto": {
"total": 116.83344174709123,
"count": 232356,
"is_parallel": true,
"self": 40.444544805036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.38889694205523,
"count": 464712,
"is_parallel": true,
"self": 76.38889694205523
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 650.4754970979052,
"count": 232357,
"self": 9.532756180015213,
"children": {
"process_trajectory": {
"total": 158.10849722389003,
"count": 232357,
"self": 156.55073405788926,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5577631660007683,
"count": 10,
"self": 1.5577631660007683
}
}
},
"_update_policy": {
"total": 482.83424369399995,
"count": 97,
"self": 412.9987791540068,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.83546453999315,
"count": 2910,
"self": 69.83546453999315
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.145000169344712e-06,
"count": 1,
"self": 1.145000169344712e-06
},
"TrainerController._save_models": {
"total": 0.1366050520000499,
"count": 1,
"self": 0.002279452000038873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13432560000001104,
"count": 1,
"self": 0.13432560000001104
}
}
}
}
}
}
}