arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1003.1630math.STstat.TH
收藏

带协变量的非参数Bandits

Nonparametric Bandits with Covariates

Philippe Rigollet, Assaf Zeevi

摘要:

我们考虑一个强盗问题,其中涉及序贯抽样从两个人口(武器)。每个手臂产生一个嘈杂的奖励实现,这取决于一个可观察到的随机协变量。目标是最大化累积期望奖励。我们推导出一般的下界的性能上的任何容许的政策,并开发一种算法,其性能达到的顺序说,下界的对数项。这是通过将全局问题分解为适当的“局部化”的强盗问题来完成的。证明融合了非参数统计和传统方法中使用的土匪文献的想法。

英文摘要:

We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random covariate. The goal is to maximize cumulative expected reward. We derive general lower bounds on the performance of any admissible policy, and develop an algorithm whose performance achieves the order of said lower bound up to logarithmic terms. This is done by decomposing the global problem into suitably "localized" bandit problems. Proofs blend ideas from nonparametric statistics and traditional methods used in the bandit literature.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑