A new kind of learning algorithm with the mechanism of intrinsic motivation - Details

Author：

Zhang, Xiaoping (Zhang, Xiaoping.) | Ruan, Xiaogang (Ruan, Xiaogang.) | Xiao, Yao (Xiao, Yao.) | Huang, Jing (Huang, Jing.)

Indexed by：

EI Scopus

Abstract：

This　paper　presents　a　new　kind　of　learning　algorithm　to　help　agents　learn　sensorimotor　skills　through　their　contact　with　the　environment.　The　learning　mechanism　is　based　on　Skinner＇s　theory　of　operant　conditioning　(OC),　which　is　improving　the　probabilities　of　good　actions,　and　reducing　the　probabilities　of　bad　actions.　The　concept　of　curiosity　is　introduced　as　the　intrinsic　motivation　for　an　agent　to　learn.　Using　this　algorithm　to　a　robot　with　the　task　of　right　handshaking,　the　effectiveness　of　the　algorithm　is　proved.　The　curiosity　in　this　paper　is　new　designed,　and　introduced　as　one　factor　that　may　affect　the　learning　process.　Its　role　and　function　are　analyzed　at　the　end　of　the　paper.　©　2016　IEEE.

Keyword：

Learning algorithms Intelligent control Motivation

Author Community：

[ 1 ] [Zhang, Xiaoping]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 2 ] [Zhang, Xiaoping]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China
[ 3 ] [Zhang, Xiaoping]Department of Psychology, Michigan State University, United States
[ 4 ] [Ruan, Xiaogang]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 5 ] [Ruan, Xiaogang]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China
[ 6 ] [Xiao, Yao]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 7 ] [Xiao, Yao]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China
[ 8 ] [Huang, Jing]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
[ 9 ] [Huang, Jing]Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China

Reprint Author's Address：

[zhang, xiaoping]department of psychology, michigan state university, united states;;[zhang, xiaoping]college of electronic information and control engineering, beijing university of technology, beijing, china;;[zhang, xiaoping]beijing key laboratory of computational intelligence and intelligent system, beijing, china

Email：

zhangxiaoping369@163.com

Show more details

Related Keywords：