|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3489169776439667, |
|
"min": 0.3489169776439667, |
|
"max": 1.4469839334487915, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10445.1787109375, |
|
"min": 10445.1787109375, |
|
"max": 43895.703125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989895.0, |
|
"min": 29952.0, |
|
"max": 989895.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989895.0, |
|
"min": 29952.0, |
|
"max": 989895.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6275317668914795, |
|
"min": -0.09911149740219116, |
|
"max": 0.705376386642456, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 175.08135986328125, |
|
"min": -23.984981536865234, |
|
"max": 201.73764038085938, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.04683122783899307, |
|
"min": -0.0729188323020935, |
|
"max": 0.2990512251853943, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 13.065912246704102, |
|
"min": -18.74013900756836, |
|
"max": 72.07134246826172, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06719487608781838, |
|
"min": 0.06481342761493966, |
|
"max": 0.07786511315144859, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9407282652294573, |
|
"min": 0.5450557920601401, |
|
"max": 1.028489025155032, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013678790159506857, |
|
"min": 0.0007324744672122727, |
|
"max": 0.01644993048726714, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.191503062233096, |
|
"min": 0.010254642540971817, |
|
"max": 0.23292076070656018, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.522468921114286e-06, |
|
"min": 7.522468921114286e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001053145648956, |
|
"min": 0.0001053145648956, |
|
"max": 0.0036325900891366995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250745714285714, |
|
"min": 0.10250745714285714, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4351044, |
|
"min": 1.3886848, |
|
"max": 2.6108633000000006, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002604949685714285, |
|
"min": 0.0002604949685714285, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003646929559999999, |
|
"min": 0.003646929559999999, |
|
"max": 0.12110524367, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01063315849751234, |
|
"min": 0.010255193337798119, |
|
"max": 0.4634004235267639, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14886422455310822, |
|
"min": 0.14357270300388336, |
|
"max": 3.243803024291992, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 298.0315789473684, |
|
"min": 278.94392523364485, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28313.0, |
|
"min": 15984.0, |
|
"max": 32792.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6598589366988132, |
|
"min": -1.0000000521540642, |
|
"max": 1.7210560562176125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 157.68659898638725, |
|
"min": -30.692601673305035, |
|
"max": 184.15299801528454, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6598589366988132, |
|
"min": -1.0000000521540642, |
|
"max": 1.7210560562176125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 157.68659898638725, |
|
"min": -30.692601673305035, |
|
"max": 184.15299801528454, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0327953547662075, |
|
"min": 0.030903595108288627, |
|
"max": 9.000462010502815, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.1155587027897127, |
|
"min": 3.0776165009010583, |
|
"max": 144.00739216804504, |
|
"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": "1678361734", |
|
"python_version": "3.8.15 (default, Nov 24 2022, 15:19:38) \n[GCC 11.2.0]", |
|
"command_line_arguments": "/nhome/siniac/cbernard/miniconda3/envs/hugging_face5/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": "1.23.5", |
|
"end_time_seconds": "1678362616" |
|
}, |
|
"total": 881.1467503271997, |
|
"count": 1, |
|
"self": 0.2217969410121441, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.03436267003417015, |
|
"count": 1, |
|
"self": 0.03436267003417015 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 880.8905907161534, |
|
"count": 1, |
|
"self": 0.7757627982646227, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.0165106672793627, |
|
"count": 1, |
|
"self": 2.0165106672793627 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 877.8678974807262, |
|
"count": 64025, |
|
"self": 0.7822886202484369, |
|
"children": { |
|
"env_step": { |
|
"total": 508.22598874755204, |
|
"count": 64025, |
|
"self": 445.60231372341514, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 62.17632272467017, |
|
"count": 64025, |
|
"self": 2.2666479535400867, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 59.909674771130085, |
|
"count": 62561, |
|
"self": 21.82704901136458, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 38.082625759765506, |
|
"count": 62561, |
|
"self": 38.082625759765506 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.44735229946672916, |
|
"count": 64025, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 879.4531953781843, |
|
"count": 64025, |
|
"is_parallel": true, |
|
"self": 483.88998732343316, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0030177850276231766, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0024100355803966522, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0006077494472265244, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0006077494472265244 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.019572174176573753, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00020107999444007874, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00017595477402210236, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00017595477402210236 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.01853463239967823, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.01853463239967823 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.000660507008433342, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00018372386693954468, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0004767831414937973, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0004767831414937973 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 395.56320805475116, |
|
"count": 64024, |
|
"is_parallel": true, |
|
"self": 11.851040678098798, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 8.51964308321476, |
|
"count": 64024, |
|
"is_parallel": true, |
|
"self": 8.51964308321476 |
|
}, |
|
"communicator.exchange": { |
|
"total": 341.5894013158977, |
|
"count": 64024, |
|
"is_parallel": true, |
|
"self": 341.5894013158977 |
|
}, |
|
"steps_from_proto": { |
|
"total": 33.6031229775399, |
|
"count": 64024, |
|
"is_parallel": true, |
|
"self": 9.047859590500593, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 24.555263387039304, |
|
"count": 512192, |
|
"is_parallel": true, |
|
"self": 24.555263387039304 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 368.85962011292577, |
|
"count": 64025, |
|
"self": 1.1922533381730318, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 81.48987087607384, |
|
"count": 64025, |
|
"self": 81.01461503095925, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.47525584511458874, |
|
"count": 2, |
|
"self": 0.47525584511458874 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 286.1774958986789, |
|
"count": 451, |
|
"self": 83.86539529636502, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 202.31210060231388, |
|
"count": 22800, |
|
"self": 202.31210060231388 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.457550287246704e-07, |
|
"count": 1, |
|
"self": 5.457550287246704e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2304192241281271, |
|
"count": 1, |
|
"self": 0.014375787228345871, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21604343689978123, |
|
"count": 1, |
|
"self": 0.21604343689978123 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |