Scholarlink

In this chapter we study infinite horizon discrete-time optimal control of Markov Decision Processes (MDPs) with finite state spaces and compact action sets and employ the long-run expected average cost criterion.

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

Uniqueness and Stability of Optimal Policies of Finite State Markov Decision Processes

  • 章节

  • 发表日期：

    2025年

查看全文
  • Alexander J. Zaslavski

摘要

In this chapter we study infinite horizon discrete-time optimal control of Markov Decision Processes (MDPs) with finite state spaces and compact action sets and employ the long-run expected average cost criterion.