|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3324046730995178, |
|
"min": 0.3324046730995178, |
|
"max": 1.51145339012146, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9918.955078125, |
|
"min": 9918.955078125, |
|
"max": 45851.44921875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989947.0, |
|
"min": 29952.0, |
|
"max": 989947.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989947.0, |
|
"min": 29952.0, |
|
"max": 989947.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6356512904167175, |
|
"min": -0.12760119140148163, |
|
"max": 0.6810547709465027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 179.88931274414062, |
|
"min": -30.24148178100586, |
|
"max": 196.14376831054688, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01655861921608448, |
|
"min": 0.008748773485422134, |
|
"max": 0.29381561279296875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.686089038848877, |
|
"min": 2.484651565551758, |
|
"max": 71.10337829589844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06834278703317978, |
|
"min": 0.06520326914959841, |
|
"max": 0.07376530641528155, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0251418054976966, |
|
"min": 0.5041903745809212, |
|
"max": 1.0809117345197592, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014557177390735079, |
|
"min": 0.0011839439733153808, |
|
"max": 0.01680611529906348, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21835766086102618, |
|
"min": 0.013023383706469188, |
|
"max": 0.2352856141868887, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.462617512493338e-06, |
|
"min": 7.462617512493338e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011193926268740007, |
|
"min": 0.00011193926268740007, |
|
"max": 0.0033830093723302996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10248750666666667, |
|
"min": 0.10248750666666667, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5373126000000001, |
|
"min": 1.3886848, |
|
"max": 2.5276697, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025850191600000015, |
|
"min": 0.00025850191600000015, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0038775287400000026, |
|
"min": 0.0038775287400000026, |
|
"max": 0.11279420303000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013626319356262684, |
|
"min": 0.013626319356262684, |
|
"max": 0.39074864983558655, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20439478754997253, |
|
"min": 0.2029009461402893, |
|
"max": 2.7352404594421387, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 309.29896907216494, |
|
"min": 273.4036697247706, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30002.0, |
|
"min": 15984.0, |
|
"max": 33059.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6288247281282218, |
|
"min": -1.0000000521540642, |
|
"max": 1.7265963141524463, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 157.99599862843752, |
|
"min": -30.326601669192314, |
|
"max": 188.19899824261665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6288247281282218, |
|
"min": -1.0000000521540642, |
|
"max": 1.7265963141524463, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 157.99599862843752, |
|
"min": -30.326601669192314, |
|
"max": 188.19899824261665, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04358661355487954, |
|
"min": 0.04135681849447375, |
|
"max": 7.892207018099725, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.227901514823316, |
|
"min": 4.227901514823316, |
|
"max": 126.2753122895956, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1677315674", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.22.4", |
|
"end_time_seconds": "1677317365" |
|
}, |
|
"total": 1690.7915436910002, |
|
"count": 1, |
|
"self": 0.32780665300015244, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10649745099999564, |
|
"count": 1, |
|
"self": 0.10649745099999564 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1690.357239587, |
|
"count": 1, |
|
"self": 1.0787967830854086, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.212022681999997, |
|
"count": 1, |
|
"self": 6.212022681999997 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1682.9902817549146, |
|
"count": 64136, |
|
"self": 1.1560017909623639, |
|
"children": { |
|
"env_step": { |
|
"total": 1067.4114520379549, |
|
"count": 64136, |
|
"self": 973.2023379759084, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 93.53008218293621, |
|
"count": 64136, |
|
"self": 4.033235828915167, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 89.49684635402105, |
|
"count": 62555, |
|
"self": 30.844650641965472, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 58.65219571205557, |
|
"count": 62555, |
|
"self": 58.65219571205557 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6790318791101981, |
|
"count": 64136, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1687.9845482259846, |
|
"count": 64136, |
|
"is_parallel": true, |
|
"self": 800.3079692010381, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005298490000086531, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0040711020003527665, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012273879997337644, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012273879997337644 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.034978249000005235, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003267969998432818, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004731770000034885, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004731770000034885 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.03320013400002608, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.03320013400002608 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.000978141000132382, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00029064899968034297, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0006874920004520391, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0006874920004520391 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 887.6765790249465, |
|
"count": 64135, |
|
"is_parallel": true, |
|
"self": 21.3382354580001, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 15.761239877952903, |
|
"count": 64135, |
|
"is_parallel": true, |
|
"self": 15.761239877952903 |
|
}, |
|
"communicator.exchange": { |
|
"total": 790.2521644959859, |
|
"count": 64135, |
|
"is_parallel": true, |
|
"self": 790.2521644959859 |
|
}, |
|
"steps_from_proto": { |
|
"total": 60.324939193007594, |
|
"count": 64135, |
|
"is_parallel": true, |
|
"self": 14.645400092902264, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 45.67953910010533, |
|
"count": 513080, |
|
"is_parallel": true, |
|
"self": 45.67953910010533 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 614.4228279259974, |
|
"count": 64136, |
|
"self": 2.097375646993214, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 136.3131885740038, |
|
"count": 64136, |
|
"self": 136.14465382500407, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.16853474899971843, |
|
"count": 2, |
|
"self": 0.16853474899971843 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 476.01226370500035, |
|
"count": 452, |
|
"self": 174.74040301798823, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 301.2718606870121, |
|
"count": 22782, |
|
"self": 301.2718606870121 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.450001587334555e-07, |
|
"count": 1, |
|
"self": 8.450001587334555e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0761375219999536, |
|
"count": 1, |
|
"self": 0.0012819069997931365, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.07485561500016047, |
|
"count": 1, |
|
"self": 0.07485561500016047 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |