English

Indexed Minimum Empirical Divergence for Unimodal Bandits

Artificial Intelligence 2021-12-03 v1 Machine Learning Optimization and Control Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2112.01452,
  title  = {Indexed Minimum Empirical Divergence for Unimodal Bandits},
  author = {Hassan Saber and Pierre Ménard and Odalric-Ambrym Maillard},
  journal= {arXiv preprint arXiv:2112.01452},
  year   = {2021}
}

Comments

NeurIPS 2021 - International Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, United States. arXiv admin note: substantial text overlap with arXiv:2006.16569, arXiv:2007.03224