Near-Optimal Representation Learning for Linear Bandits and Linear RL

             Jiachen Hu * 1 Xiaoyu Chen * 1 Chi Jin 2 Lihong Li 3 Liwei Wang 1 4

             Abstract                 While representation learning has achieved tremendous suc-
                                  cess in a variety of applications (Bengio et al., 2013), its
   This paper studies representation learning for        theoretical understanding is still limited. A widely accepted
   multi-task linear bandits and mul ...