Bandit problems with side observations
Bandit problems with side observations
复制标题
侧面观察的强盗问题
DOI：
10.1109/tac.2005.844079
复制
发表时间：
2005
影响因子：
6.8
通讯作者：
F. I. H. Vincent Poor
中科院分区：
文献类型：
--
作者：
Student Member Ieee Chih;F. I. Sanjeev R. Kulkarni;F. I. H. Vincent Poor
传统的双臂强盗问题被认为是一个扩展，其中决策者有机会获得一些侧信息，然后再决定哪只手臂拉。在每个时间t，在做出选择之前，决策者能够观察到随机变量X/sub t/，该随机变量提供了关于要获得的奖励的一些信息。重点是找到一致的好规则（最小化劣采样时间的增长率）和量化额外信息的帮助。各种设置被认为是每个设置，可实现的下采样时间的下限和渐近最优的自适应计划实现这些下限的建设。
An extension of the traditional two-armed bandit problem is considered, in which the decision maker has access to some side information before deciding which arm to pull. At each time t, before making a selection, the decision maker is able to observe a random variable X/sub t/ that provides some information on the rewards to be obtained. The focus is on finding uniformly good rules (that minimize the growth rate of the inferior sampling time) and on quantifying how much the additional information helps. Various settings are considered and for each setting, lower bounds on the achievable inferior sampling time are developed and asymptotically optimal adaptive schemes achieving these lower bounds are constructed.