TURNPIKES IN FINITE MARKOV DECISION PROCESSES AND RANDOM WALK*

被引:0
|
作者
Piunovskiy, A. B. [1 ]
机构
[1] Univ Liverpool, Dept Math Sci, Liverpool, England
关键词
Markov decision process; discounted reward; average reward; random walk; stochastic knapsack problem; turnpike;
D O I
10.1137/S0040585X97T991325
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this paper we revise the theory of turnpikes in discounted Markov decision pro-cesses, prove the turnpike theorem for the undiscounted model, and apply the results to the specific random walk.
引用
收藏
页码:123 / 149
页数:27
相关论文
共 50 条