|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7193378210067749, |
|
"min": 0.7193378210067749, |
|
"max": 1.4446152448654175, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 21430.51171875, |
|
"min": 21430.51171875, |
|
"max": 43823.84765625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479958.0, |
|
"min": 29952.0, |
|
"max": 479958.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479958.0, |
|
"min": 29952.0, |
|
"max": 479958.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.0014545751037076116, |
|
"min": -0.10955612361431122, |
|
"max": 0.010393742471933365, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 0.3549163341522217, |
|
"min": -26.403026580810547, |
|
"max": 2.5360732078552246, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.023472020402550697, |
|
"min": 0.015917571261525154, |
|
"max": 0.27981844544410706, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.7271728515625, |
|
"min": 3.88388729095459, |
|
"max": 67.15642547607422, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07004561483698926, |
|
"min": 0.0647162001807287, |
|
"max": 0.07332476972232518, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9806386077178497, |
|
"min": 0.47409147852275724, |
|
"max": 1.0998715458348778, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0047728536348244826, |
|
"min": 0.0007883337277327705, |
|
"max": 0.0067429235388655724, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.06681995088754275, |
|
"min": 0.005518336094129394, |
|
"max": 0.08874566259337192, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.121806435591428e-05, |
|
"min": 2.121806435591428e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029705290098279994, |
|
"min": 0.00029705290098279994, |
|
"max": 0.0030807188730937996, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10707265714285716, |
|
"min": 0.10707265714285716, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4990172000000002, |
|
"min": 1.3382272, |
|
"max": 2.3371452000000006, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007165584485714284, |
|
"min": 0.0007165584485714284, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.010031818279999999, |
|
"min": 0.010031818279999999, |
|
"max": 0.10271792937999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.021641161292791367, |
|
"min": 0.021641161292791367, |
|
"max": 0.5224998593330383, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.30297625064849854, |
|
"min": 0.30297625064849854, |
|
"max": 3.657498836517334, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 896.3225806451613, |
|
"min": 851.1111111111111, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 27786.0, |
|
"min": 15984.0, |
|
"max": 32177.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.15988004778822262, |
|
"min": -1.0000000521540642, |
|
"max": 0.03741662928627597, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -4.796401433646679, |
|
"min": -32.000001668930054, |
|
"max": 1.346998654305935, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.15988004778822262, |
|
"min": -1.0000000521540642, |
|
"max": 0.03741662928627597, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -4.796401433646679, |
|
"min": -32.000001668930054, |
|
"max": 1.346998654305935, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.2018311425286811, |
|
"min": 0.2018311425286811, |
|
"max": 10.59727288596332, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.0549342758604325, |
|
"min": 6.0549342758604325, |
|
"max": 169.55636617541313, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1670432199", |
|
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1.21.6", |
|
"end_time_seconds": "1670433202" |
|
}, |
|
"total": 1002.706004702, |
|
"count": 1, |
|
"self": 0.4458975420000115, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10769680499998913, |
|
"count": 1, |
|
"self": 0.10769680499998913 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1002.1524103549999, |
|
"count": 1, |
|
"self": 0.6362640589875355, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.625565632999951, |
|
"count": 1, |
|
"self": 11.625565632999951 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 989.7979242120124, |
|
"count": 31592, |
|
"self": 0.7240554370092696, |
|
"children": { |
|
"env_step": { |
|
"total": 634.2472531480032, |
|
"count": 31592, |
|
"self": 576.3080644289876, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 57.54083206700466, |
|
"count": 31592, |
|
"self": 2.3566585610108177, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 55.18417350599384, |
|
"count": 31301, |
|
"self": 18.607391880003377, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 36.57678162599046, |
|
"count": 31301, |
|
"self": 36.57678162599046 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.39835665201104575, |
|
"count": 31592, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 999.7336648219984, |
|
"count": 31592, |
|
"is_parallel": true, |
|
"self": 476.16684518701027, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006209933000036472, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003635849999909624, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0025740830001268478, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0025740830001268478 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.048661046000006536, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005101570000647371, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044678399996200824, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044678399996200824 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04600221700002294, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04600221700002294 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017018879999568526, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045269899999311747, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012491889999637351, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012491889999637351 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 523.5668196349882, |
|
"count": 31591, |
|
"is_parallel": true, |
|
"self": 14.242781030978449, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.129994064998925, |
|
"count": 31591, |
|
"is_parallel": true, |
|
"self": 12.129994064998925 |
|
}, |
|
"communicator.exchange": { |
|
"total": 447.7451992450011, |
|
"count": 31591, |
|
"is_parallel": true, |
|
"self": 447.7451992450011 |
|
}, |
|
"steps_from_proto": { |
|
"total": 49.448845294009686, |
|
"count": 31591, |
|
"is_parallel": true, |
|
"self": 11.771353873988176, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 37.67749142002151, |
|
"count": 252728, |
|
"is_parallel": true, |
|
"self": 37.67749142002151 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 354.82661562699997, |
|
"count": 31592, |
|
"self": 1.1799178489939095, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 79.23333572300533, |
|
"count": 31592, |
|
"self": 79.12105718500527, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11227853800005505, |
|
"count": 1, |
|
"self": 0.11227853800005505 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 274.41336205500073, |
|
"count": 213, |
|
"self": 105.04202057599827, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 169.37134147900247, |
|
"count": 11466, |
|
"self": 169.37134147900247 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 7.979999736562604e-07, |
|
"count": 1, |
|
"self": 7.979999736562604e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09265565300006529, |
|
"count": 1, |
|
"self": 0.001639704999888636, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09101594800017665, |
|
"count": 1, |
|
"self": 0.09101594800017665 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |