Search Machine Learning Repository: @inproceedings{icml2014c2_ailon14,
    Publisher = {JMLR Workshop and Conference Proceedings},
    Title = {Reducing Dueling Bandits to Cardinal Bandits},
    Url = {http://jmlr.org/proceedings/papers/v32/ailon14.pdf},
    Abstract = {We present algorithms for reducing the Dueling Bandits problem to the conventional (stochastic) Multi-Armed Bandits problem. The Dueling Bandits problem is an online model of learning with ordinal feedback of the form ``A is preferred to B'' (as opposed to cardinal feedback like ``A has value 2.5''), giving it wide applicability in learning from implicit user feedback and revealed and stated preferences. In contrast to existing algorithms for the Dueling Bandits problem, our reductions -- named $\Doubler$, $\MultiSbm$ and $\DoubleSbm$ -- provide a generic schema for translating the extensive body of known results about conventional Multi-Armed Bandit algorithms to the Dueling Bandits setting. For $\Doubler$ and $\MultiSbm$ we prove regret upper bounds in both finite and infinite settings, and conjecture about the performance of $\DoubleSbm$ which empirically outperforms the other two as well as previous algorithms in our experiments. In addition, we provide the first almost optimal regret bound in terms of second order terms, such as the differences between the values of the arms.},
    Author = {Nir Ailon and Zohar Karnin and Thorsten Joachims},
    Editor = {Tony Jebara and Eric P. Xing},
    Year = {2014},
    Booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)},
    Pages = {856-864}
   }