|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4877895414829254, |
|
"min": 0.4877895414829254, |
|
"max": 1.4276467561721802, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14750.755859375, |
|
"min": 14750.755859375, |
|
"max": 43309.09375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989971.0, |
|
"min": 29985.0, |
|
"max": 989971.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989971.0, |
|
"min": 29985.0, |
|
"max": 989971.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3313111960887909, |
|
"min": -0.10459650307893753, |
|
"max": 0.461904913187027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 87.79747009277344, |
|
"min": -25.103160858154297, |
|
"max": 123.79051971435547, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.6019312739372253, |
|
"min": -0.61241215467453, |
|
"max": 0.6019312739372253, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 159.51177978515625, |
|
"min": -160.4519805908203, |
|
"max": 159.51177978515625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0682120603700501, |
|
"min": 0.06434755042343766, |
|
"max": 0.07310072194824259, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9549688451807016, |
|
"min": 0.5117050536376981, |
|
"max": 1.042244601577598, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.06812883828977301, |
|
"min": 0.00031434256763016787, |
|
"max": 0.06812883828977301, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.9538037360568221, |
|
"min": 0.0037721108115620146, |
|
"max": 0.9538037360568221, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.666061730392857e-06, |
|
"min": 7.666061730392857e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010732486422549999, |
|
"min": 0.00010732486422549999, |
|
"max": 0.0035072270309243997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10255532142857145, |
|
"min": 0.10255532142857145, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4357745000000002, |
|
"min": 1.3886848, |
|
"max": 2.5690756, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026527661071428573, |
|
"min": 0.00026527661071428573, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037138725500000004, |
|
"min": 0.0037138725500000004, |
|
"max": 0.11693065244000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006950224284082651, |
|
"min": 0.006950224284082651, |
|
"max": 0.35153621435165405, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09730313718318939, |
|
"min": 0.09730313718318939, |
|
"max": 2.4607534408569336, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 508.672131147541, |
|
"min": 412.87142857142857, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31029.0, |
|
"min": 16784.0, |
|
"max": 33024.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.2617409566386801, |
|
"min": -0.9999000518582761, |
|
"max": 1.5585542600069726, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 76.96619835495949, |
|
"min": -31.996801659464836, |
|
"max": 109.09879820048809, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.2617409566386801, |
|
"min": -0.9999000518582761, |
|
"max": 1.5585542600069726, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 76.96619835495949, |
|
"min": -31.996801659464836, |
|
"max": 109.09879820048809, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03641195466945169, |
|
"min": 0.03412701004395226, |
|
"max": 6.754271524355692, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.2211292348365532, |
|
"min": 2.2182556528568966, |
|
"max": 114.82261591404676, |
|
"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": "1657309006", |
|
"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": "1657311122" |
|
}, |
|
"total": 2116.146267751, |
|
"count": 1, |
|
"self": 0.48194089599974177, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.043788979999931144, |
|
"count": 1, |
|
"self": 0.043788979999931144 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2115.620537875, |
|
"count": 1, |
|
"self": 1.5764783300428462, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.003945166999983, |
|
"count": 1, |
|
"self": 10.003945166999983 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2103.946173620957, |
|
"count": 63591, |
|
"self": 1.5861168209839889, |
|
"children": { |
|
"env_step": { |
|
"total": 1338.7314306589508, |
|
"count": 63591, |
|
"self": 1226.159380111992, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 111.75133710099931, |
|
"count": 63591, |
|
"self": 4.817163276003271, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 106.93417382499604, |
|
"count": 62549, |
|
"self": 36.33038118001116, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 70.60379264498488, |
|
"count": 62549, |
|
"self": 70.60379264498488 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8207134459595409, |
|
"count": 63591, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2111.54045398497, |
|
"count": 63591, |
|
"is_parallel": true, |
|
"self": 990.234894074963, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005513232999987849, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00412801499987836, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013852180001094894, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013852180001094894 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05224870300003204, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005017249999355045, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00028810300000259303, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00028810300000259303 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.049762918000055834, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.049762918000055834 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016959570000381063, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045111800022823445, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001244838999809872, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001244838999809872 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1121.305559910007, |
|
"count": 63590, |
|
"is_parallel": true, |
|
"self": 29.06304668602661, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.354639281003642, |
|
"count": 63590, |
|
"is_parallel": true, |
|
"self": 24.354639281003642 |
|
}, |
|
"communicator.exchange": { |
|
"total": 970.7875338350049, |
|
"count": 63590, |
|
"is_parallel": true, |
|
"self": 970.7875338350049 |
|
}, |
|
"steps_from_proto": { |
|
"total": 97.10034010797199, |
|
"count": 63590, |
|
"is_parallel": true, |
|
"self": 24.395352890857794, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 72.7049872171142, |
|
"count": 508720, |
|
"is_parallel": true, |
|
"self": 72.7049872171142 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 763.628626141022, |
|
"count": 63591, |
|
"self": 2.800404878980885, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 174.346729461034, |
|
"count": 63591, |
|
"self": 174.13018816303418, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21654129799981092, |
|
"count": 2, |
|
"self": 0.21654129799981092 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 586.4814918010071, |
|
"count": 451, |
|
"self": 231.45633428899566, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 355.02515751201145, |
|
"count": 22788, |
|
"self": 355.02515751201145 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.193000116472831e-06, |
|
"count": 1, |
|
"self": 1.193000116472831e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09393956400026582, |
|
"count": 1, |
|
"self": 0.0016233070005000627, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09231625699976576, |
|
"count": 1, |
|
"self": 0.09231625699976576 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |