Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem

Masrour Zoghi, Shimon Whiteson, Remi Munos, Maarten Rijke
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):10-18, 2014.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v32-zoghi14, title = {Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem}, author = {Zoghi, Masrour and Whiteson, Shimon and Munos, Remi and Rijke, Maarten}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {10--18}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/zoghi14.pdf}, url = {https://proceedings.mlr.press/v32/zoghi14.html}, 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.} }
Endnote
%0 Conference Paper %T Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem %A Masrour Zoghi %A Shimon Whiteson %A Remi Munos %A Maarten Rijke %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-zoghi14 %I PMLR %P 10--18 %U https://proceedings.mlr.press/v32/zoghi14.html %V 32 %N 2 %X 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.
RIS
TY - CPAPER TI - Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem AU - Masrour Zoghi AU - Shimon Whiteson AU - Remi Munos AU - Maarten Rijke BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/06/18 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-zoghi14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 2 SP - 10 EP - 18 L1 - http://proceedings.mlr.press/v32/zoghi14.pdf UR - https://proceedings.mlr.press/v32/zoghi14.html AB - 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. ER -
APA
Zoghi, M., Whiteson, S., Munos, R. & Rijke, M.. (2014). Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(2):10-18 Available from https://proceedings.mlr.press/v32/zoghi14.html.

Related Material