|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.39757049083709717, |
|
"min": 0.39757049083709717, |
|
"max": 1.3595595359802246, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11920.75390625, |
|
"min": 11920.75390625, |
|
"max": 41243.59765625, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 899956.0, |
|
"min": 29885.0, |
|
"max": 899956.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 899956.0, |
|
"min": 29885.0, |
|
"max": 899956.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4898543655872345, |
|
"min": -0.0930364727973938, |
|
"max": 0.5115171074867249, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 132.26068115234375, |
|
"min": -22.421789169311523, |
|
"max": 139.13265991210938, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.09477725625038147, |
|
"min": -0.09477725625038147, |
|
"max": 0.4064110219478607, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -25.589859008789062, |
|
"min": -25.589859008789062, |
|
"max": 96.31941223144531, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06938424920921939, |
|
"min": 0.06483511217628184, |
|
"max": 0.07380248141961257, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0407637381382908, |
|
"min": 0.5904198513569006, |
|
"max": 1.0407637381382908, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015227381634112032, |
|
"min": 0.0006474719040076074, |
|
"max": 0.01643273844057971, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22841072451168049, |
|
"min": 0.008213004547359109, |
|
"max": 0.23005833816811597, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 4.973965008711112e-06, |
|
"min": 4.973965008711112e-06, |
|
"max": 0.00029417966860677773, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 7.460947513066668e-05, |
|
"min": 7.460947513066668e-05, |
|
"max": 0.003448147817284111, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10165795555555555, |
|
"min": 0.10165795555555555, |
|
"max": 0.1980598888888889, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5248693333333334, |
|
"min": 1.4705237777777782, |
|
"max": 2.543327111111111, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00017562976, |
|
"min": 0.00017562976, |
|
"max": 0.009806182900000002, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0026344464, |
|
"min": 0.0026344464, |
|
"max": 0.1149533173, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013464792631566525, |
|
"min": 0.013354185037314892, |
|
"max": 0.5027457475662231, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2019718885421753, |
|
"min": 0.18695859611034393, |
|
"max": 4.021965980529785, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 386.56, |
|
"min": 353.8780487804878, |
|
"max": 999.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28992.0, |
|
"min": 17579.0, |
|
"max": 33190.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.560093317826589, |
|
"min": -0.9999742455059483, |
|
"max": 1.5994320809841156, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 117.00699883699417, |
|
"min": -31.995201662182808, |
|
"max": 129.55399855971336, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.560093317826589, |
|
"min": -0.9999742455059483, |
|
"max": 1.5994320809841156, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 117.00699883699417, |
|
"min": -31.995201662182808, |
|
"max": 129.55399855971336, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05361438301566523, |
|
"min": 0.05361438301566523, |
|
"max": 10.323105855948395, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.021078726174892, |
|
"min": 4.021078726174892, |
|
"max": 185.8159054070711, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657738490", |
|
"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": "1657740373" |
|
}, |
|
"total": 1882.9600919249997, |
|
"count": 1, |
|
"self": 0.42833328099959544, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.054805991999728576, |
|
"count": 1, |
|
"self": 0.054805991999728576 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1882.4769526520004, |
|
"count": 1, |
|
"self": 1.3027695909495378, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.473618197000178, |
|
"count": 1, |
|
"self": 6.473618197000178 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1874.6021489080504, |
|
"count": 57289, |
|
"self": 1.4039689420374089, |
|
"children": { |
|
"env_step": { |
|
"total": 1219.1033666070125, |
|
"count": 57289, |
|
"self": 1119.6238383419636, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 98.8068662120113, |
|
"count": 57289, |
|
"self": 4.268505632986944, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 94.53836057902436, |
|
"count": 56309, |
|
"self": 32.348266454005625, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.19009412501873, |
|
"count": 56309, |
|
"self": 62.19009412501873 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.672662053037584, |
|
"count": 57289, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1878.9325053499733, |
|
"count": 57289, |
|
"is_parallel": true, |
|
"self": 852.3902138780068, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019260659996689355, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007521909992647124, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001173875000404223, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001173875000404223 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04927950499995859, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047984999901018455, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000427511000452796, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000427511000452796 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04671544400025596, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04671544400025596 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016567000002396526, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004194039997855725, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00123729600045408, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00123729600045408 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1026.5422914719666, |
|
"count": 57288, |
|
"is_parallel": true, |
|
"self": 25.48484664891157, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 21.37142343792675, |
|
"count": 57288, |
|
"is_parallel": true, |
|
"self": 21.37142343792675 |
|
}, |
|
"communicator.exchange": { |
|
"total": 894.4486843141308, |
|
"count": 57288, |
|
"is_parallel": true, |
|
"self": 894.4486843141308 |
|
}, |
|
"steps_from_proto": { |
|
"total": 85.23733707099746, |
|
"count": 57288, |
|
"is_parallel": true, |
|
"self": 21.078682677283723, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 64.15865439371373, |
|
"count": 458304, |
|
"is_parallel": true, |
|
"self": 64.15865439371373 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 654.0948133590005, |
|
"count": 57289, |
|
"self": 2.4162042220768853, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 149.28206904092258, |
|
"count": 57289, |
|
"self": 149.1674607319228, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11460830899977736, |
|
"count": 1, |
|
"self": 0.11460830899977736 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 502.396540096001, |
|
"count": 408, |
|
"self": 196.61358089001578, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 305.7829592059852, |
|
"count": 20532, |
|
"self": 305.7829592059852 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1089996405644342e-06, |
|
"count": 1, |
|
"self": 1.1089996405644342e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0984148470006403, |
|
"count": 1, |
|
"self": 0.0017685410002741264, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09664630600036617, |
|
"count": 1, |
|
"self": 0.09664630600036617 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |