摘要
研究可数状态空间任意行动空间非一致性有界费用马氏决策过程(MDP)的强平均最优,给出了使得每个常用的平均最优策略也是强平均最优的条件,并实质性的推广了Cavazos-Cadena和Fernandez-Gaucheran(Math.Meth.Oper.Res.,1996,43:281-300)的主要结果.
In this paper, we consider the Markov decision processes under an average cost criterion with non-uniformly bounded cost, denumerable state and arbitrary action spaces. Some sufficient conditions are given under which every average optimal policy is strong average optimal. We improve the main results obtained by Cavazos-Cadena R.and Fernandez-Gaucheran E. (Math. Meth. Oper. Res., 1996, 43: 281-300).
出处
《运筹学学报》
CSCD
2010年第1期95-105,共11页
Operations Research Transactions
基金
湖南省自然科学基金项目(08JJ3004)
湖南省社会科学基金项目(08YBB187)的支持
关键词
运筹学
马氏决策过程(MDP)
强平均费用准则
非一致有界费用
充分条件
Operations research, Markov decision processes, strong average optimal- itv crikerion, non-uniformly bounded cost, sufficient conditions