On average reward semi-markov decision processes with a general multichain structure

• 成果类型: Article
• 署名作者: Jianyong, L; Xiaobo, Z
• 署名单位: Chinese Academy of Sciences; Tsinghua University
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X
• DOI: 10.1287/moor.1030.0077
• 发表日期: 2004
• 页码: 339-352
• 关键词: optimality equation; optimal policies; EXISTENCE; state

摘要

In this paper we investigate average reward semi-Markov decision processes with a general multichain structure using a data-transformation method. By solving the transformed discrete-time average Markov decision processes, we can obtain significant and interesting information on the original average semi-Markov decision processes. If the original semi-Markov decision processes satisfy some appropriate conditions, then stationary optimal policies in the transformed discrete-time models are also optimal in the original semi-Markov decision processes.