On the Optimality of Perturbations in Stochastic and
Adversarial Multi-armed Bandit Problems
Baekjin Kim Ambuj Tewari
Department of Statistics Department of Statistics
University of Michigan University of Michigan
Ann Arbor, MI 48109 Ann Arbor, MI 48109
baekjin@umich.edu tewaria@umich.edu
Abstract
We investigate the optimality of perturbation based algorithms ...


雷达卡


京公网安备 11010802022788号







