首页 | 本学科首页   官方微博 | 高级检索  
     


An iterative procedure for nondiscounted discrete-time markov decisions
Authors:Gary J. Koehler  Andrew B. Whinston  Gordon P. Wright
Abstract:This paper considers the problem of computing, by iterative methods, optimal policies for Markov decision processes. The policies computed are optimal for all sufficiently small interest rates.
Keywords:
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号