Kernel-Based Reinforcement Learning: A Finite-Time Analysis

     Omar D. Domingues 1 2 Pierre Menard 3 Matteo Pirotta 4 Emilie Kaufmann 1 5 Michal Valko 1 5 6

             Abstract                 in the face of uncertainty (OFU, Jaksch et al. 2010) and
                                  Thompson Sampling (Strens, 2000; Osband et al., 2013)
    We consider the exploration-exploitation dilemma
                                  principles have been used to design algorithms with sublin-
    in f ...