Scholarlink

We apply methods of the fixed point theory to a Lambda policy iteration with a randomization algorithm for weak contractions mappings. This type of mappings covers a broader range than the strong contractions typically considered in the literature, such as Ćirić contraction. Specifically, we explore the characteristics of reinforcement learning procedures developed for feedback control within the context of fixed point theory. Under relatively general assumptions, we identify the sufficient conditions for convergence with a probability of one in infinite-dimensional policy spaces.

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

Fixed Point Theory Analysis of a Lambda Policy Iteration with Randomization for the Ćirić Contraction Operator

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Abdelkader Belhenniche,
  • Roman Chertovskih

摘要

We apply methods of the fixed point theory to a Lambda policy iteration with a randomization algorithm for weak contractions mappings. This type of mappings covers a broader range than the strong contractions typically considered in the literature, such as Ćirić contraction. Specifically, we explore the characteristics of reinforcement learning procedures developed for feedback control within the context of fixed point theory. Under relatively general assumptions, we identify the sufficient conditions for convergence with a probability of one in infinite-dimensional policy spaces.