arrow
返回

An efficient L2-norm regularized least-squares temporal difference learning algorithm

delete2013-06-01
delete16
PRE
AI
S
Shenglei Chen *
G
Geng Chen
DOI:10.1016/j.knosys.2013.02.010delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
In reinforcement learning, when samples are limited in some real applications, Least-Squares Temporal Difference (LSTD) learning is prone to over-fitting, which can be overcome by the introduction of regularization. However, the solution of LSTD with regularization still depends on costly matrix inversion operations. In this paper we investigate the L2-norm regularized LSTD learning and propose an efficient algorithm to avoid expensive computational cost. We derive LSTD using Bellman operator along with projection operator. The L2-norm penalty is introduced to avoid over-fitting. We also describe the difference between Bellman residual minimization and LSTD. Then we propose an efficient recursive least-squares algorithm for L2-norm regularized LSTD, which can eliminate matrix inversion operations and decrease computational complexity effectively. We present empirical comparisons on the Boyan chain problem. The results show that the performance of the new algorithm is better than that of regularized LSTD. (C) 2013 Elsevier B.V. All rights reserved.
Keyword:
Reinforcement learning
Temporal difference
Recursive least-squares
Bellman residual minimizations
Regularization
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

K
Knowledge-Based Systems
IF:
7.6
论文数:
1.2W
被引数:
4.5W

机构

Nanjing Audit University 封面图
Nanjing Audit University
学者数:
1.0K
论文数: 1.3K
被引数: 1.3K
引用论文

引用论文

Opening Platforms: How, When and Why?
err2008-01-01
err0
PREAI
errThomas R. Eisenmann; Geoffrey Parker; Marshall W. Van Alstyne
err分享
err收藏
SNF Interim Storage Canister Corrosion and Surface Environment Investigations (FY22 Status Update)
err
IF0
err2022-09-28
err0
errOAAI
errRebecca Schaller; Andrew Knight; Ryan Katona; Brendan Nation; Erin Karasz; Charles Bryan
err分享
err收藏
Tropical-Forest Density Profiles from Multibaseline Interferometric SAR
err2006-07-01
err0
PREAI
errR.N. Treuhaft; B.D. Chapman; J.R. dos Santos; L.V. Dutra; F.G. Goncalves; C. da Costa Freitas; J.C. Mura; P.M. de Alencastro Graca; J.B. Drake
err分享
err收藏
学者 查看更多内容