SIA OpenIR  > 机器人学研究室
基于增量式RBF网络的Q学习算法
Alternative TitleQ-Learning Algorithm Based on Incremental RBF Network
胡艳明1,2,3; 李德才1,2; 何玉庆1,2; 韩建达1,2,4
Department机器人学研究室
Source Publication机器人
ISSN1002-0446
2019
Volume41Issue:5Pages:562-573
Contribution Rank1
Funding Organization国家自然科学基金(U1608253,91748208)
Keyword核方法 最小二乘算法 增量式学习 移动机器人 Q学习
Abstract为提升机器人的行为智能水平,提出一种基于增量式径向基函数网络(IRBFN)的Q学习(IRBFNQL)算法.其核心是通过结构的自适应增长与参数的在线学习,实现对Q值函数的学习与存储,从而使机器人可以在未知环境中自主增量式地学习行为策略.首先,采用近似线性独立(ALD)准则在线增加网络节点,使机器人的记忆容量伴随状态空间的拓展自适应增长.同时,节点的增加意味着网络拓扑内部连接的改变.采用核递归最小二乘(KRLS)算法更新网络拓扑连接关系及参数,使机器人不断扩展与优化自身的行为策略.此外,为避免过拟合问题,将L2正则项融合到KRLS算法中,得到L2约束下的核递归最小二乘算法(L2KRLS).实验结果表明,IRBFN-QL算法能够实现机器人与未知环境的自主交互,并逐步提高移动机器人在走廊环境中的导航行为能力.
Other AbstractAn IRBFN (incremental radial basis function network) based Q-learning (IRBFN-QL) algorithm is proposed to upgrade the behavioural intelligence of robots. The key is to learn and store Q-value function based on adaptive growth of the structure and online learning of the parameters, to make robots learn the behavioral strategy autonomously and incrementally in unknown environment. Firstly, approximate linear independence (ALD) criterion is used to online increase the network nodes, thus the memory capacity of robots can grow adaptively along with the expansion of state space. The new added nodes change the inner connection of network topology. Kernel recursive least square (KRLS) algorithm is used to update the connection of network topology and its parameters, therefore the robot can extend and optimize its behavioral strategy con- stantly. Besides, L2 regularization term is integrated to KRLS algorithm to avoid the overfitting problem, which forms the L2 constrained KRLS (L2KRLS) algorithm. The experimental results show that IRBFN-QL algorithm can realize autonomous interaction between the robot and the unknown environment and gradually improve the navigation behavior ability of mobile robot in corridor environments.
Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/24934
Collection机器人学研究室
Corresponding Author何玉庆
Affiliation1.中国科学院沈阳自动化研究所机器人学国家重点实验室
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学
4.南开大学人工智能学院
Recommended Citation
GB/T 7714
胡艳明,李德才,何玉庆,等. 基于增量式RBF网络的Q学习算法[J]. 机器人,2019,41(5):562-573.
APA 胡艳明,李德才,何玉庆,&韩建达.(2019).基于增量式RBF网络的Q学习算法.机器人,41(5),562-573.
MLA 胡艳明,et al."基于增量式RBF网络的Q学习算法".机器人 41.5(2019):562-573.
Files in This Item:
File Name/Size DocType Version Access License
基于增量式RBF网络的Q学习算法.pdf(649KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[胡艳明]'s Articles
[李德才]'s Articles
[何玉庆]'s Articles
Baidu academic
Similar articles in Baidu academic
[胡艳明]'s Articles
[李德才]'s Articles
[何玉庆]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[胡艳明]'s Articles
[李德才]'s Articles
[何玉庆]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于增量式RBF网络的Q学习算法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.