Now showing items 1-1 of 1

    • Gambler's ruin bandit problem 

      Akbarzadeh, Nima; Tekin, Cem (IEEE, 2017)
      In this paper, we propose a new multi-armed bandit problem called the Gambler's Ruin Bandit Problem (GRBP). In the GRBP, the learner proceeds in a sequence of rounds, where each round is a Markov Decision Process (MDP) ...