|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3652462661266327, |
|
"min": 0.35558298230171204, |
|
"max": 1.4143867492675781, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11027.515625, |
|
"min": 10693.759765625, |
|
"max": 42906.8359375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989976.0, |
|
"min": 29952.0, |
|
"max": 989976.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989976.0, |
|
"min": 29952.0, |
|
"max": 989976.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.49422723054885864, |
|
"min": -0.11669795215129852, |
|
"max": 0.49422723054885864, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 131.46444702148438, |
|
"min": -27.774112701416016, |
|
"max": 131.46444702148438, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.018996428698301315, |
|
"min": 0.007305871229618788, |
|
"max": 0.5553948879241943, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.0530500411987305, |
|
"min": 1.884914755821228, |
|
"max": 131.6285858154297, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06665942495289658, |
|
"min": 0.06563412556259245, |
|
"max": 0.07392641945142982, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9332319493405521, |
|
"min": 0.5174849361600087, |
|
"max": 1.0447802424023394, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01383853923297942, |
|
"min": 0.00010542718356777116, |
|
"max": 0.014246269452303836, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19373954926171186, |
|
"min": 0.0011596990192454827, |
|
"max": 0.1994477723322537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.0140457298804812e-05, |
|
"min": 1.0140457298804812e-05, |
|
"max": 0.0002951986437503818, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00014196640218326736, |
|
"min": 0.00014196640218326736, |
|
"max": 0.0032284872525504948, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10338012022630837, |
|
"min": 0.10338012022630837, |
|
"max": 0.19839954738330975, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.447321683168317, |
|
"min": 1.3887968316831683, |
|
"max": 2.321582277227723, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0003476740106082038, |
|
"min": 0.0003476740106082038, |
|
"max": 0.009840114783592644, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.004867436148514853, |
|
"min": 0.004867436148514853, |
|
"max": 0.10762862138613861, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.014419575221836567, |
|
"min": 0.014419575221836567, |
|
"max": 0.5946853756904602, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2018740475177765, |
|
"min": 0.2018740475177765, |
|
"max": 4.162797451019287, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 402.3466666666667, |
|
"min": 402.3466666666667, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30176.0, |
|
"min": 15984.0, |
|
"max": 33290.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4376106444001198, |
|
"min": -1.0000000521540642, |
|
"max": 1.4376106444001198, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 107.82079833000898, |
|
"min": -31.998401671648026, |
|
"max": 107.82079833000898, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4376106444001198, |
|
"min": -1.0000000521540642, |
|
"max": 1.4376106444001198, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 107.82079833000898, |
|
"min": -31.998401671648026, |
|
"max": 107.82079833000898, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05992915028550973, |
|
"min": 0.05992915028550973, |
|
"max": 12.075403152033687, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.494686271413229, |
|
"min": 4.386309638386592, |
|
"max": 193.206450432539, |
|
"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": "1673796949", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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": "1.21.6", |
|
"end_time_seconds": "1673799016" |
|
}, |
|
"total": 2067.0185086229994, |
|
"count": 1, |
|
"self": 0.47671244299954196, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11826165299999047, |
|
"count": 1, |
|
"self": 0.11826165299999047 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2066.423534527, |
|
"count": 1, |
|
"self": 1.2653916589838445, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.7974483289999625, |
|
"count": 1, |
|
"self": 6.7974483289999625 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2058.269175276017, |
|
"count": 64034, |
|
"self": 1.3027417352045632, |
|
"children": { |
|
"env_step": { |
|
"total": 1359.7551954319529, |
|
"count": 64034, |
|
"self": 1250.82816550896, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 108.10615614007065, |
|
"count": 64034, |
|
"self": 4.466587902997617, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 103.63956823707304, |
|
"count": 63178, |
|
"self": 34.732174530935936, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 68.9073937061371, |
|
"count": 63178, |
|
"self": 68.9073937061371 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8208737829222628, |
|
"count": 64034, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2061.9042876479475, |
|
"count": 64034, |
|
"is_parallel": true, |
|
"self": 912.8860802919512, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017428930000278342, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00061219900044307, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011306939995847642, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011306939995847642 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04727561699974103, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005343569996512088, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005241029998614977, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005241029998614977 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.044465932000093744, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.044465932000093744 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001751225000134582, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046358900090126554, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012876359992333164, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012876359992333164 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1149.0182073559963, |
|
"count": 64033, |
|
"is_parallel": true, |
|
"self": 29.62406433598244, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.328380398967056, |
|
"count": 64033, |
|
"is_parallel": true, |
|
"self": 24.328380398967056 |
|
}, |
|
"communicator.exchange": { |
|
"total": 988.8844497450455, |
|
"count": 64033, |
|
"is_parallel": true, |
|
"self": 988.8844497450455 |
|
}, |
|
"steps_from_proto": { |
|
"total": 106.18131287600136, |
|
"count": 64033, |
|
"is_parallel": true, |
|
"self": 23.21197597377659, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 82.96933690222477, |
|
"count": 512264, |
|
"is_parallel": true, |
|
"self": 82.96933690222477 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 697.2112381088596, |
|
"count": 64034, |
|
"self": 2.2577392447446982, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 150.28269188411969, |
|
"count": 64034, |
|
"self": 150.0749842261198, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20770765799989022, |
|
"count": 2, |
|
"self": 0.20770765799989022 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 544.6708069799952, |
|
"count": 438, |
|
"self": 210.1910749380395, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 334.4797320419557, |
|
"count": 23040, |
|
"self": 334.4797320419557 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0739995559561066e-06, |
|
"count": 1, |
|
"self": 1.0739995559561066e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09151818899954378, |
|
"count": 1, |
|
"self": 0.0013942409996161587, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09012394799992762, |
|
"count": 1, |
|
"self": 0.09012394799992762 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |