Reinforcement Learning Algorithms Based on Dynamic Programming

基于动态规划的强化学习算法

• 批准号: 9214866
• 负责人: Andrew Barto
• 金额: $ 31.63万
• 依托单位: University of Massachusetts Amherst
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1992
• 资助国家: 美国
• 起止时间: 1992-09-15 至 1997-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9214866&HistoricalAwards=false
• 关键词: Reinforcement; Learning; Algorithms; Based; Dynamic

This project will investigate aspects of a class of reinforcement learning algorithms based on dynamic programming (DP). Although these algorithms have been widely studied and have been experimented with in many applications, their theory is not developed enough to permit a clear understanding of the classes of problems for which they may be the methods of choice, or to guide their application. Research at the University of Massachusetts has made considerable recent progress in relating these methods to the most closely related conventional methods and in understanding the factors that influence their performance, both successful and unsuccessful. These methods may provide the only computationally feasible approaches to very large and analytically intractable sequential decision problems. The objectives of this project are: 1) to continue development of DP-based reinforcement learning methods an their theory, 2) to investigate their computational complexity, and 3) to define the characteristics of problems for which they are best suited.

该项目将调查一个 强化学习类 动态算法 编程（DP）。 虽然这些 算法已经被广泛研究， 已经在许多国家进行了实验 应用程序， 他们的理论不是 发展到足以让一个清晰的 对问题类别的理解 它们可能是 选择，或指导其应用。 大学的研究 马萨诸塞州已经取得了相当大的成就 最近的进展，这些 最密切相关的方法 常规方法并且 了解影响 他们的表现，既成功， 不成功。 这些方法可以 提供了唯一的计算 可行的办法， 解析难处理的序列 决策问题。这一目标 项目是：1）继续发展 基于DP的强化学习 方法和理论，2） 研究其计算 复杂性，以及3）定义 问题的特点， 他们是最合适的。