Scholarlink

<p>We consider a Markov decision process (MDP), whose total discounted utility is aggregated recursively with a concave discount function that is not necessarily linear. The state and action spaces are Borel spaces, and the utility function is nonnegative. We show that it can be reduced to a turn-based stochastic game model with the total undiscounted utility. This reduction result is then applied to the MDP problem with recursively aggregated utility to be maximized or cost to be minimized.</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

Reduction of a Markov decision process with non-linear discounting to a stochastic game with standard total undiscounted criterion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月11日

查看全文
  • Alexey Piunovskiy,
  • Ernst Presman,
  • Yi Zhang,
  • Xinran Zheng

摘要

We consider a Markov decision process (MDP), whose total discounted utility is aggregated recursively with a concave discount function that is not necessarily linear. The state and action spaces are Borel spaces, and the utility function is nonnegative. We show that it can be reduced to a turn-based stochastic game model with the total undiscounted utility. This reduction result is then applied to the MDP problem with recursively aggregated utility to be maximized or cost to be minimized.