Further Contributions to the "Two-Armed Bandit" Problem
The Annals of Statistics · 1985 · Volume 13 · Issue 1
Abstract
A version of the two-armed bandit with two states of nature and two repeatable experiments is studied. With an infinite horizon and with or without discounting, an optimal procedure is to perform one experiment whenever the posterior probability of one of the states of nature exceeds a constant $\xi^\ast$, and perform the other experiment whenever the posterior is less than $\xi^\ast$ with indifference when the posterior equals $\xi^\ast. \xi^\ast$ is expressed in terms involving expectations of ladder variables and can be calculated using Spitzer series.
Keywords
62L05, 62L10, dynamic programming, Random walks, sequential design
Enable JavaScript for citation tools and additional paper interactions.