| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
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.
Cited literature [26 references]
https://hal.inria.fr/hal-01225614
Contributor : Pratik Gajane <>
Submitted on : Thursday, January 14, 2016 - 1:37:23 PM
Last modification on : Friday, March 22, 2019 - 1:35:17 AM
Document(s) archivé(s) le : Friday, April 15, 2016 - 2:31:39 PM
Contributor : Pratik Gajane <>
Submitted on : Thursday, January 14, 2016 - 1:37:23 PM
Last modification on : Friday, March 22, 2019 - 1:35:17 AM
Document(s) archivé(s) le : Friday, April 15, 2016 - 2:31:39 PM
