Search Machine Learning Repository: @inproceedings{icml2014c2_zoghi14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem},
    Url = {http://jmlr.org/proceedings/papers/v32/zoghi14.pdf},
    Abstract = {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 sharp finite-time regret bound of order O(K log t) on a very general class of dueling bandit problems that matches a lower bound proven in (Yue et al., 2012). In addition, our empirical results using real data from an information retrieval application show that it greatly outperforms the state of the art.},
    Author = {Masrour Zoghi and Shimon Whiteson and Remi Munos and Maarten D. Rijke},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {10-18}
   }