Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rectangularity and Duality of Distributionally Robust Markov Decision Processes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月3日

查看全文
  • Yan Li,
  • Alexander Shapiro

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.