Dynamic Planning and Learning under Recovering Rewards
David Simchi-Levi 1 Zeyu Zheng 2 Feng Zhu 1
Abstract immediately drops after it is pulled, and then gradually re-
Motivated by emerging applications such as live- covers if the arm is not pulled in the subsequent time periods.
streaming e-commerce, promotions and recom- This class of problems are motivated by emerging applica-
mendations, we introduce a general class ...


雷达卡




京公网安备 11010802022788号







