Logarithmic Regret for Reinforcement Learning with Linear Function
                 Approximation

                   Jiafan He 1 Dongruo Zhou 1 Quanquan Gu 1

             Abstract                 A common approach to cope with high-dimensional state
   Reinforcement learning (RL) with linear function       and action spaces is to utilize function approximation such
   approximation has received increasing attention       as linear functions or neural networks to map states and
   recently. How ...