@article{Xu_Honda_Sugiyama_2019, title={Dueling Bandits with Qualitative Feedback}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4496}, DOI={10.1609/aaai.v33i01.33015549}, abstractNote={<p>We formulate and study a novel multi-armed bandit problem called the <em>qualitative dueling bandit (QDB)</em> problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the <em>dueling bandit</em> (DB) problem where the duel is carried out by comparing the qualitative feedback. Although we can naively use classic DB algorithms for solving the QDB problem, this reduction significantly worsens the performanceâ€”actually, in the QDB problem, the probability that one arm wins the duel over another arm can be <em>directly</em> estimated without carrying out actual duels. In this paper<sup>1</sup>, we propose such direct algorithms for the QDB problem. Our theoretical analysis shows that the proposed algorithms significantly outperform DB algorithms by incorporating the qualitative feedback, and experimental results also demonstrate vast improvement over the existing DB algorithms.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Xu, Liyuan and Honda, Junya and Sugiyama, Masashi}, year={2019}, month={Jul.}, pages={5549-5556} }