运筹学学报
運籌學學報
운주학학보
OR TRANSACTIONS
2010年
1期
95-105
,共11页
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
運籌學%馬氏決策過程(MDP)%彊平均費用準則%非一緻有界費用%充分條件
운주학%마씨결책과정(MDP)%강평균비용준칙%비일치유계비용%충분조건
Operations research%Markov decision processes%strong average optimal-ity criterion%non-uniformly bounded cost%sufficient conditions
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.
研究可數狀態空間任意行動空間非一緻性有界費用馬氏決策過程(MDP)的彊平均最優,給齣瞭使得每箇常用的平均最優策略也是彊平均最優的條件,併實質性的推廣瞭Cavazos-Cadena和Fernandez-Gaucheran(Math.Meth.Oper.Res.,1996,43:281-300)的主要結果.
연구가수상태공간임의행동공간비일치성유계비용마씨결책과정(MDP)적강평균최우,급출료사득매개상용적평균최우책략야시강평균최우적조건,병실질성적추엄료Cavazos-Cadena화Fernandez-Gaucheran(Math.Meth.Oper.Res.,1996,43:281-300)적주요결과.
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).