arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1203.4640math.OCmath.PR
收藏

多臂强盗,有约束

The Multi-Armed Bandit, with Constraints

Eric V. Denardo, Eugene A. Feinberg, Uriel G. Rothblum

摘要:

本文的前几部分提出了一个马尔可夫决策模型,被称为多臂土匪的假设下,决策者的效用函数是线性或指数的分析。该分析包括计算与使用优先政策相关的预期效用和确定最佳优先政策的有效程序。这些章节中的方法是新颖的,建立在使用基本行运算的基础上。在本文的后面部分中,对分析进行了调整,以适应将土匪联系起来的约束。

英文摘要:

The early sections of this paper present an analysis of a Markov decision model that is known as the multi-armed bandit under the assumption that the utility function of the decision maker is either linear or exponential. The analysis includes efficient procedures for computing the expected utility associated with the use of a priority policy and for identifying a priority policy that is optimal. The methodology in these sections is novel, building on the use of elementary row operations. In the later sections of this paper, the analysis is adapted to accommodate constraints that link the bandits.

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。

↑