On Average Optimality for Non-Stationary Markov Decision Processes in Borel Spaces

• 成果类型: Article; Early Access
• 署名作者: Guo, Xin; Huang, Yonghui; Zhang, Yi
• 署名单位: Sun Yat Sen University; Sun Yat Sen University; University of Birmingham
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X
• DOI: 10.1287/moor.2023.0169
• 发表日期: 2024
• 关键词: state-space; criterion; CONVERGENCE

摘要

This paper studies Borel models of nonstationary Markov decision processes (MDPs) with average criteria. We establish a suitable fixed point theorem, which is used to show the existence of solutions to the average optimality equation (AOE), without using contractions. The existence of optimal policies follows from the obtained solutions to the AOE. Furthermore, we show that versions of the rolling horizon algorithm can be used to produce an optimal policy or an epsilon-optimal policy. Finally, we compare the optimality conditions imposed in this paper with the existing ones in the literature, and demonstrate that they can be satisfied while the previous ones are not.