期刊
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
卷 56, 期 9, 页码 2128-2139出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAC.2011.2115290
关键词
Approximation methods; dynamic programming; Markov decision processes; reinforcement learning; temporal difference methods
资金
- NSF [ECCS-0801549]
We consider projected equations for approximate solution of high-dimensional fixed point problems within low-dimensional subspaces. We introduce an analytical framework based on an equivalence with variational inequalities, and algorithms that may be implemented with low-dimensional simulation. These algorithms originated in approximate dynamic programming (DP), where they are collectively known as temporal difference (TD) methods. Even when specialized to DP, our methods include extensions/new versions of TD methods, which offer special implementation advantages and reduced overhead over the standard LSTD and LSPE methods, and can deal with near singularity in the associated matrix inversion. We develop deterministic iterative methods and their simulation-based versions, and we discuss a sharp qualitative distinction between them: the performance of the former is greatly affected by direction and feature scaling, yet the latter have the same asymptotic convergence rate regardless of scaling, because of their common simulation-induced performance bottleneck.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据