Random Walk Bandits

Bandit learning problems find important applications ranging from medical trials to online advertisement. In this paper, we study a novel bandit learning problem motivated by recommender systems. The goal is to recommend items so that users are likely to continue browsing. Our model views a user's browsing record as a random walk over a graph of webpages. This random walk ends (hits an absorbing node) when the user exits the website. Our model introduces a novel learning problem that calls for new technical insights on learning with graph random walk feedback. In particular, the performance and complexity depend on the structure of the decision space (represented by graphs). Our paper provides a comprehensive understanding of this new problem. We provide bandit learning algorithms for this problem with provable performance guarantees, and provide matching lower bounds.