|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1852513700723648, |
|
"min": 0.1828487664461136, |
|
"max": 1.5463743209838867, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5557.541015625, |
|
"min": 5459.1328125, |
|
"max": 46910.8125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999912.0, |
|
"min": 29932.0, |
|
"max": 2999912.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999912.0, |
|
"min": 29932.0, |
|
"max": 2999912.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7237173318862915, |
|
"min": -0.13040199875831604, |
|
"max": 0.8135476112365723, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 211.32545471191406, |
|
"min": -31.296480178833008, |
|
"max": 245.69137573242188, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.006164701655507088, |
|
"min": -0.024830089882016182, |
|
"max": 0.20712080597877502, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.8000929355621338, |
|
"min": -6.952425003051758, |
|
"max": 49.08763122558594, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06884813228806648, |
|
"min": 0.06506748594983948, |
|
"max": 0.07557280880960092, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9638738520329306, |
|
"min": 0.5113399944520066, |
|
"max": 1.1017595254793289, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015028054526893236, |
|
"min": 6.47512603286681e-05, |
|
"max": 0.016954349202153805, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2103927633765053, |
|
"min": 0.0007770151239440172, |
|
"max": 0.23736088883015327, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4765209364309457e-06, |
|
"min": 1.4765209364309457e-06, |
|
"max": 0.00029841125767243813, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.067129311003324e-05, |
|
"min": 2.067129311003324e-05, |
|
"max": 0.0036757754747415664, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049214047619048, |
|
"min": 0.10049214047619048, |
|
"max": 0.19947041904761906, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4068899666666668, |
|
"min": 1.3962929333333334, |
|
"max": 2.7074662000000003, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.9164833571428365e-05, |
|
"min": 5.9164833571428365e-05, |
|
"max": 0.009947094862857142, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008283076699999971, |
|
"min": 0.0008283076699999971, |
|
"max": 0.12254331749, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.003426314564421773, |
|
"min": 0.0033297636546194553, |
|
"max": 0.2763366103172302, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.04796840250492096, |
|
"min": 0.04661669209599495, |
|
"max": 1.9343562126159668, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 265.14406779661016, |
|
"min": 227.2258064516129, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31287.0, |
|
"min": 16603.0, |
|
"max": 33687.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6859355781669334, |
|
"min": -0.9999500517733395, |
|
"max": 1.7707741815716989, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 198.94039822369814, |
|
"min": -31.998401656746864, |
|
"max": 227.8107985854149, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6859355781669334, |
|
"min": -0.9999500517733395, |
|
"max": 1.7707741815716989, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 198.94039822369814, |
|
"min": -31.998401656746864, |
|
"max": 227.8107985854149, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.009489890193219901, |
|
"min": 0.008390802981703319, |
|
"max": 5.34306164918577, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.1198070427999482, |
|
"min": 1.0152871607861016, |
|
"max": 90.83204803615808, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657461670", |
|
"python_version": "3.9.5 (default, Nov 23 2021, 15:27:38) \n[GCC 9.3.0]", |
|
"command_line_arguments": "/local_disk0/.ephemeral_nfs/envs/pythonEnv-fb4aed1f-7c07-4ca5-b819-aeecdc6ccb9f/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": "1.20.3", |
|
"end_time_seconds": "1657466363" |
|
}, |
|
"total": 4692.737395972001, |
|
"count": 1, |
|
"self": 0.2702085850014555, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.08080957099991792, |
|
"count": 1, |
|
"self": 0.08080957099991792 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 4692.386377815999, |
|
"count": 1, |
|
"self": 3.9103825940128445, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 12.672993666000366, |
|
"count": 1, |
|
"self": 12.672993666000366 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 4675.684551769987, |
|
"count": 193767, |
|
"self": 3.925852716826739, |
|
"children": { |
|
"env_step": { |
|
"total": 2830.8489869019786, |
|
"count": 193767, |
|
"self": 2515.6984759872616, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 312.56576160497843, |
|
"count": 193767, |
|
"self": 12.271461569627718, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 300.2943000353507, |
|
"count": 187568, |
|
"self": 98.993900600497, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 201.30039943485372, |
|
"count": 187568, |
|
"self": 201.30039943485372 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.584749309738527, |
|
"count": 193767, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4685.897691749033, |
|
"count": 193767, |
|
"is_parallel": true, |
|
"self": 2412.6613520708115, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001852370000051451, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009680760003902833, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008842939996611676, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008842939996611676 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.025506631000098423, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00038378000044758664, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002961400000458525, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002961400000458525 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.023825390999718365, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.023825390999718365 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0010013199998866185, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00023629300039829104, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0007650269994883274, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0007650269994883274 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2273.236339678221, |
|
"count": 193766, |
|
"is_parallel": true, |
|
"self": 67.02309798906845, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 41.81772355412431, |
|
"count": 193766, |
|
"is_parallel": true, |
|
"self": 41.81772355412431 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1991.822494931881, |
|
"count": 193766, |
|
"is_parallel": true, |
|
"self": 1991.822494931881 |
|
}, |
|
"steps_from_proto": { |
|
"total": 172.5730232031474, |
|
"count": 193766, |
|
"is_parallel": true, |
|
"self": 40.4992663508242, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 132.07375685232319, |
|
"count": 1550128, |
|
"is_parallel": true, |
|
"self": 132.07375685232319 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1840.9097121511813, |
|
"count": 193767, |
|
"self": 6.888272713986225, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 396.20563162719054, |
|
"count": 193767, |
|
"self": 395.4405441641902, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7650874630003273, |
|
"count": 6, |
|
"self": 0.7650874630003273 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1437.8158078100046, |
|
"count": 1381, |
|
"self": 572.8118601500323, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 865.0039476599723, |
|
"count": 68415, |
|
"self": 865.0039476599723 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.019997039809823e-07, |
|
"count": 1, |
|
"self": 8.019997039809823e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11844898399976955, |
|
"count": 1, |
|
"self": 0.0008768910001890617, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11757209299958049, |
|
"count": 1, |
|
"self": 0.11757209299958049 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |