Rectangularity and Duality of Distributionally Robust Markov Decision Processes

• 成果类型: Article; Early Access
• 署名作者: Li, Yan; Shapiro, Alexander
• 署名单位: Texas A&M University System; Texas A&M University College Station; University System of Georgia; Georgia Institute of Technology
• 刊物名称: MATHEMATICAL PROGRAMMING
• ISSN/ISSBN: 0025-5610; 1436-4646
• DOI: 10.1007/s10107-025-02297-y
• 发表日期: 2025-11-03
• 关键词: Markov decision process; distributional robustness; Game formulation; Strong Duality; Risk measures

摘要

The main goal of this paper is to discuss several approaches to the formulation of distributionally robust counterparts of Markov Decision Processes, where the transition kernels are not specified exactly but rather are assumed to be elements of the corresponding ambiguity sets. The intent is to clarify some connections between the game and static formulations of distributionally robust MDPs, and delineate the role of rectangularity associated with ambiguity sets in determining these connections.