Channel selection with Rayleigh fading: A multi-armed bandit framework

Channel Selection in fading environments with no prior information on the channels´ quality is a challenging issue. In the case of `Rayleigh channels´ the measured Signal-To-Noise Ratio follows exponential distributions. Thus, we suggest in this paper a simple algorithm that deals with resource selection when the measured samples are drawn from exponential distributions. This strategy, referred to as Multiplicative Upper Confidence Bound Algorithm (MUCB), associates a utility index to every available arm, and then selects the arm with the highest index. For every arm, the associated index is equal to the product of a multiplicative factor by the sample mean of the rewards collected by this arm. We show that MUCB policies are order optimal. Moreover simulations illustrate and validate the stated theoretical results.