SIMPLE EMERGENT ACTION REPRESENTATIONS FROM MULTI -TASK POLICY TRAINING Pu Hua14 Yubei Chen2 Huazhe Xu134
SIMPLEEMERGENTACTIONREPRESENTATIONSFROMMULTI-TASKPOLICYTRAININGPuHua1,4,YubeiChen2,HuazheXu1,3,41TsinghuaUniversity,2CenterforDataScience,NewYorkUniversity,3ShanghaiAILab,4ShanghaiQiZhiInstituteABSTRACTThelow-levelsensoryandmotorsignalsindeepreinforcementlearning,whichexistinhigh-dimensionalspaces...
2025-05-03
6.68MB 22 页 4
0
10玖币