open access

https://hdl.handle.net/2115/47057

Algorithms for Adversarial Bandit Problems with Multiple Plays

英語

online learning

2010

Springer Berlin / Heidelberg

Adversarial bandit problems studied by Auer et al. [4] are multi-armed bandit problems in which no stochastic assumption is made on the nature of the process generating the rewards for actions. In this paper, we extend their theories to the case where k(≥ 1) distinct actions are selected at each time step. As algorithms to solve our problem, we analyze an extension of Exp3 [4] and an application of a bandit online linear optimization algorithm [1] in addition to two existing algorithms (Exp3, ComBand [5]) in terms of time and space efficiency and the regret for the best fixed action set. The extension of Exp3, called Exp3. M, performs best with respect to both the measures: it runs in O(K(log k + 1)) time and O(K) space, and suffers at most O(√kTK log(K/k)) regret, where K is the number of possible actions and T is the number of iterations. The upper bound of the regret we proved for Exp3. M is an extension of that proved by Auer et al. for Exp 3.

図書（部分）

Accepted Manuscript

The original publication is available at www.springerlink.com