Now showing items 1-1 of 1

    • A Structured Multiarmed Bandit Problem and the Greedy Policy 

      Rusmevichientong, Paat; Mersereau, Adam J.; Tsitsiklis, John N. (Institute of Electrical and Electronics Engineers, 2009-12)
      We consider a multiarmed bandit problem where the expected reward of each arm is a linear function of an unknown scalar with a prior distribution. The objective is to choose a sequence of arms that maximizes the expected ...