非齐次马氏决策过程的齐次化

The Homogenization of Non-homogeneous Markov Decision Processes

该文考虑的是可数状态空间有限行动空间非齐次马氏决策过程的期望总报酬准则．与以往不同的是，我们是通过扩大状态空间的方法，将非齐次的马氏决策过程转化成齐次的马氏决策过程，于是非常简洁地得到了按传统的方法所得的主要结果．

In this paper we consider the homogenization of Non-homogneous Markov deci-sion model with expected total reward criterion.denumerable state space and finite actionspaces. We translate the non-homogeneous Markov decision processes into a homegeneousone by the method of extanding state space which is different from the usual one, and thenwe easily obtain the mail results obtained by usual method. Specially, the mail results ob-tained by K. Hinderer'