arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.01029eess.SYcs.DScs.NAcs.SYmath.NAmath.OC
收藏

Lambda-策略迭代:综述与新实现

Lambda-Policy Iteration: A Review and a New Implementation

M.I.T.(麻省理工学院)

Dimitri P. Bertsekas

AI总结:

本文综述了lambda-策略迭代方法,探讨其在动态规划中的应用,提出新的实现方式以改进传统策略迭代方法的性能。

摘要:

本文讨论了lambda-策略迭代,一种用于精确和近似动态规划的方法。它介于经典价值迭代(VI)和策略迭代(PI)方法之间,并与乐观(也称为修改)PI密切相关,其中每次策略评估均使用有限次数的VI进行近似。我们回顾了该方法的理论及其在基于模拟的成本函数近似中的偏差和探索问题。随后讨论了各种实现,这些实现优于传统PI方法中使用LSPE(λ)、LSTD(λ)或TD(λ)进行策略评估的成本函数近似。其中一种实现基于新的模拟方案,称为几何抽样,其使用多个短轨迹而非单个无限长轨迹。

英文摘要:

In this paper we discuss $ł$-policy iteration, a method for exact and approximate dynamic programming. It is intermediate between the classical value iteration (VI) and policy iteration (PI) methods, and it is closely related to optimistic (also known as modified) PI, whereby each policy evaluation is done approximately, using a finite number of VI. We review the theory of the method and associated questions of bias and exploration arising in simulation-based cost function approximation. We then discuss various implementations, which offer advantages over well-established PI methods that use LSPE($ł$), LSTD($ł$), or TD($ł$) for policy evaluation with cost function approximation. One of these implementations is based on a new simulation scheme, called geometric sampling, which uses multiple short trajectories rather than a single infinitely long trajectory.

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。

↑