|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.775467574596405, |
|
"min": 0.775467574596405, |
|
"max": 1.4535527229309082, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23400.509765625, |
|
"min": 23400.509765625, |
|
"max": 44094.9765625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479957.0, |
|
"min": 29975.0, |
|
"max": 479957.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479957.0, |
|
"min": 29975.0, |
|
"max": 479957.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.325147807598114, |
|
"min": -0.10404781997203827, |
|
"max": 0.37916868925094604, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 85.51387023925781, |
|
"min": -24.763381958007812, |
|
"max": 100.85887145996094, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.10621927678585052, |
|
"min": -0.21033114194869995, |
|
"max": 0.22147221863269806, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 27.9356689453125, |
|
"min": -55.948081970214844, |
|
"max": 53.596275329589844, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06863481113261607, |
|
"min": 0.06468206482739852, |
|
"max": 0.07105041485679589, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.960887355856625, |
|
"min": 0.4823158504454761, |
|
"max": 1.0401752325803197, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01161268330475696, |
|
"min": 0.0014182857658531186, |
|
"max": 0.021181143804849353, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.16257756626659745, |
|
"min": 0.014182857658531186, |
|
"max": 0.3177171570727403, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.052703601482857e-05, |
|
"min": 2.052703601482857e-05, |
|
"max": 0.0002904748317464857, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00028737850420759996, |
|
"min": 0.00028737850420759996, |
|
"max": 0.0030659805780066, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10684231428571427, |
|
"min": 0.10684231428571427, |
|
"max": 0.1968249428571429, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4957923999999998, |
|
"min": 1.3777746000000002, |
|
"max": 2.4219934, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000693547197142857, |
|
"min": 0.000693547197142857, |
|
"max": 0.009682811791428571, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009709660759999999, |
|
"min": 0.009709660759999999, |
|
"max": 0.10223714065999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01488067489117384, |
|
"min": 0.014855831861495972, |
|
"max": 0.43215659260749817, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2083294540643692, |
|
"min": 0.2083294540643692, |
|
"max": 3.0250961780548096, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 549.8360655737705, |
|
"min": 484.8474576271187, |
|
"max": 993.5, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 33540.0, |
|
"min": 16518.0, |
|
"max": 33540.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.0825199653704962, |
|
"min": -0.9277467176318168, |
|
"max": 1.3248866386711597, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 64.95119792222977, |
|
"min": -29.345001719892025, |
|
"max": 79.49319832026958, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.0825199653704962, |
|
"min": -0.9277467176318168, |
|
"max": 1.3248866386711597, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 64.95119792222977, |
|
"min": -29.345001719892025, |
|
"max": 79.49319832026958, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.08535324649274116, |
|
"min": 0.07551089621354211, |
|
"max": 8.468867305885343, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.12119478956447, |
|
"min": 4.455142876598984, |
|
"max": 143.97074420005083, |
|
"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": "1657556153", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \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": "1657557164" |
|
}, |
|
"total": 1010.4290942160001, |
|
"count": 1, |
|
"self": 0.4359122689998003, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04097649600021214, |
|
"count": 1, |
|
"self": 0.04097649600021214 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1009.952205451, |
|
"count": 1, |
|
"self": 0.6580836910122798, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.072324406999996, |
|
"count": 1, |
|
"self": 10.072324406999996 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 999.1261248929877, |
|
"count": 31773, |
|
"self": 0.6877285939872309, |
|
"children": { |
|
"env_step": { |
|
"total": 648.0082168149713, |
|
"count": 31773, |
|
"self": 596.1937606409804, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 51.46355741701018, |
|
"count": 31773, |
|
"self": 2.246374353032479, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 49.2171830639777, |
|
"count": 31299, |
|
"self": 17.113333896963923, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 32.10384916701378, |
|
"count": 31299, |
|
"self": 32.10384916701378 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.35089875698076867, |
|
"count": 31773, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1007.9281917560099, |
|
"count": 31773, |
|
"is_parallel": true, |
|
"self": 460.7510374319986, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.008449707999943712, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0053065460001562315, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0031431619997874805, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0031431619997874805 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.047349387999929604, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005596359999344713, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044537999997373845, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044537999997373845 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04448806699997476, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04448806699997476 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001856305000046632, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005825400003232062, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012737649997234257, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012737649997234257 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 547.1771543240113, |
|
"count": 31772, |
|
"is_parallel": true, |
|
"self": 13.797195006033462, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.369438549985489, |
|
"count": 31772, |
|
"is_parallel": true, |
|
"self": 11.369438549985489 |
|
}, |
|
"communicator.exchange": { |
|
"total": 476.31782719302896, |
|
"count": 31772, |
|
"is_parallel": true, |
|
"self": 476.31782719302896 |
|
}, |
|
"steps_from_proto": { |
|
"total": 45.692693574963414, |
|
"count": 31772, |
|
"is_parallel": true, |
|
"self": 11.238211301847741, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.45448227311567, |
|
"count": 254176, |
|
"is_parallel": true, |
|
"self": 34.45448227311567 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 350.43017948402917, |
|
"count": 31773, |
|
"self": 1.172426093031845, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 79.70617045799895, |
|
"count": 31773, |
|
"self": 79.60031695199882, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10585350600013044, |
|
"count": 1, |
|
"self": 0.10585350600013044 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 269.5515829329984, |
|
"count": 219, |
|
"self": 105.58953385600375, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 163.96204907699462, |
|
"count": 11406, |
|
"self": 163.96204907699462 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1260003702773247e-06, |
|
"count": 1, |
|
"self": 1.1260003702773247e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09567133399968952, |
|
"count": 1, |
|
"self": 0.0016238129996963835, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09404752099999314, |
|
"count": 1, |
|
"self": 0.09404752099999314 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |