Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret

In this paper we consider the problem of learning the optimal policy for the uncontrolled restless bandit problem. In this problem only the state of the selected arm can be observed, the state transitions are independent of control and the transition law is unknown. We propose a learning algorithm which gives logarithmic regret uniformly over time with respect to the optimal finite horizon policy with known transition law under some assumptions on the transition probabilities of the arms and the structure of the optimal stationary policy for the infinite horizon average reward problem.