arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.7380cs.AI
收藏

POMDPs的策略空间搜索求解

Solving POMDPs by Searching in Policy Space

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Eric A. Hansen

摘要:

用于求解POMDPs的大多数算法迭代地改进隐式地表示策略的价值函数,并且被称为在价值函数空间中搜索。本文提出了一种解决POMDPs的方法,该方法将策略显式表示为有限状态控制器,并通过在策略空间中搜索来迭代改进控制器。两个相关的算法说明了这种方法。第一个是策略迭代算法,可以在解决无限时域POMDPs的价值迭代。它提供了一个新的启发式搜索算法的基础,承诺进一步加速的计算工作集中在区域的问题空间是可达到的,或可能达到的,从一个开始状态。

英文摘要:

Most algorithms for solving POMDPs iteratively improve a value function that implicitly represents a policy and are said to search in value function space. This paper presents an approach to solving POMDPs that represents a policy explicitly as a finite-state controller and iteratively improves the controller by search in policy space. Two related algorithms illustrate this approach. The first is a policy iteration algorithm that can outperform value iteration in solving infinitehorizon POMDPs. It provides the foundation for a new heuristic search algorithm that promises further speedup by focusing computational effort on regions of the problem space that are reachable, or likely to be reached, from a start state.

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。

↑