arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.00219math.OCecon.TH
收藏

基于Q变换的无界动态规划

Unbounded Dynamic Programming via the Q-Transform

Qingyin Ma, John Stachurski, Alexis Akira Toda

摘要:

我们提出了一种新的方法来解决动态判定问题无限奖励的基础上使用的Q-学习的转换。在我们的例子中,变换的目标是将无界动态规划转换为有界动态规划。该方法足够通用,可以处理现有方法难以解决的问题,而且相对于其他技术来说很简单,可以用于应用工作。我们通过例子表明,许多常见的判定问题满足我们的条件。

英文摘要:

We propose a new approach to solving dynamic decision problems with unbounded rewards based on the transformations used in Q-learning. In our case, the objective of the transform is to convert an unbounded dynamic program into a bounded one. The approach is general enough to handle problems for which existing methods struggle, and yet simple relative to other techniques and accessible for applied work. We show by example that many common decision problems satisfy our conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑