The Symmetry between Arms and Knapsacks:
A Primal-Dual Approach for Bandits with Knapsacks
Xiaocheng Li 1 Chunlin Sun 2 Yinyu Ye 2
Abstract mark problem for decision making under uncertainty that
In this paper, we study the bandits with knapsacks has been studied for nearly a century. As a prototypical
(BwK) problem and develop a primal-dual based reinforcement learning problem, MAB problem exemplifes
algorithm ...


雷达卡




京公网安备 11010802022788号







