Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem
This addresses the challenge of decision-making with pairwise comparisons in bandit problems, which is incremental as it adapts an existing algorithm to a specific variation.
The paper tackles the K-armed dueling bandit problem by proposing a method that extends the Upper Confidence Bound algorithm to handle relative feedback, achieving a finite-time regret bound of O(log t) and outperforming state-of-the-art methods in real-world information retrieval applications.
This paper proposes a new method for the K-armed dueling bandit problem, a variation on the regular K-armed bandit problem that offers only relative feedback about pairs of arms. Our approach extends the Upper Confidence Bound algorithm to the relative setting by using estimates of the pairwise probabilities to select a promising arm and applying Upper Confidence Bound with the winner as a benchmark. We prove a finite-time regret bound of order O(log t). In addition, our empirical results using real data from an information retrieval application show that it greatly outperforms the state of the art.