Provably Efficient Reinforcement Learning for Discounted MDPs with
                 Feature Mapping

                   Dongruo Zhou 1 Jiafan He 1 Quanquan Gu 1

            Abstract                 linear functions or neural networks to map states and actions
   Modern tasks in reinforcement learning have large      to a low-dimensional space and solve the decision-making
   state and action spaces. To deal with them effi-      problem in the feature space. Despite the empirical success
   cien ...