In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g. [0,1]. However, the derived regret bound is described in an asymptotic form and the performance in finite time has been unknown. We inspect this policy and derive a finite-time regret bound by refining large deviation probabilities to a simple finite form. Further, this observation reveals that the assumption on the lower-boundedness of the support is not essential and can be replaced with a weaker one, the existence of the moment generating function.
A conversion theorem and minimax optimality for continuum contextual bandits
University of Oxford CMAP, Ecole Polytechnique, IP Paris(牛津大学计算机应用数学中心,巴黎高等技术学院,IP巴黎);CMAP, Ecole Polytechnique, IP Paris(计算机应用数学中心,巴黎高等技术学院,IP巴黎);CSML, Istituto Italiano di Tecnologia University College London(计算机科学与机器学习,意大利技术研究所,伦敦大学学院);CREST, ENSAE, IP Paris(CREST,ENSAE,IP巴黎)
Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
Division of Decision and Control Systems(决策与控制系统系);KTH Royal Institute of Technology(皇家理工学院);Laboratoire des signaux et systèmes(信号与系统实验室);Université Paris-Saclay, CNRS, CentraleSupélec(巴黎萨克雷大学、国家科学研究中心、中央理工-巴黎高等理工学院)