Indexed Minimum Empirical Divergence for Unimodal Bandits
Saber, Hassan, Ménard, Pierre, Maillard, Odalric-Ambrym
–arXiv.org Artificial Intelligence
We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure. We introduce IMED-UB, a algorithm that optimally exploits the unimodal-structure, by adapting to this setting the Indexed Minimum Empirical Divergence (IMED) algorithm introduced by Honda and Takemura [2015]. Owing to our proof technique, we are able to provide a concise finite-time analysis of IMED-UB algorithm. Numerical experiments show that IMED-UB competes with the state-of-the-art algorithms.
arXiv.org Artificial Intelligence
Dec-2-2021