Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

                      Yaqi Duan 1 Chi Jin 2 Zhiyuan Li 3

             Abstract                 algorithms including support vector machines (Cortes &
                                 Vapnik, 1995; Suykens & Vandewalle, 1999), boosting (Fre-
   This paper considers batch Reinforcement Learn-
                                 und et al., 1996; Schapire, 1999), as well as many success-
   ing (RL) with general value function app ...