ICML 2015poster55 citations

A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits

Pratik Gajane, Tanguy Urvoy, Fabrice Clérot

Abstract

We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this algorithm and a general lower bound of order omega(sqrt(KT)). At the end, we provide experimental results using real data from information retrieval applications.

BibTeX
@InProceedings{pmlr-v37-gajane15,
  title = 	 {A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits},
  author = 	 {Gajane, Pratik and Urvoy, Tanguy and Clérot, Fabrice},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {218--227},
  year = 	 {2015},
  editor = 	 {Bach, Francis and Blei, David},
  volume = 	 {37},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Lille, France},
  month = 	 {07--09 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v37/gajane15.pdf},
  url = 	 {https://proceedings.mlr.press/v37/gajane15.html},
  abstract = 	 {We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this algorithm and a general lower bound of order omega(sqrt(KT)). At the end, we provide experimental results using real data from information retrieval applications.}
}