General Gittins index processes in discrete time.
收藏PubMed Central1993-02-15 更新2026-05-16 收录
下载链接：
https://pmc.ncbi.nlm.nih.gov/articles/PMC45846/
下载链接
链接失效反馈官方服务：
资源简介：
We combine the formulation of Mandelbaum [Mandelbaum, A. (1986) Probab. Theory Rel. Fields 71, 129-147] with ideas from Whittle [Whittle, P. (1980) J. R. Stat. Soc. B 42, 143-149] to obtain a simple and constructive proof for the optimality of Gittins index processes in the general, nonmarkovian dynamic allocation (or "multi-armed bandit") problem. Our approach also provides an explicit expression for the value of this problem.
提供机构：
National Academy of Sciences
创建时间：
1993-02-15
