The research on reinforcement learning based on robocup - 文章详情页

作者：

Han, Guang-Sheng (Han, Guang-Sheng.) | Zhang, Hong-Wei (Zhang, Hong-Wei.)

收录：

EI Scopus PKU CSCD

摘要：

Keepaway-a　sub-problem　of　Robocup,　has　been　elevated　from　machine　learning　testbed　to　the　domain　to　a　machine　learning　benchmark,　which　is　much　suitable　for　comparing　different　learning　algorithms.　This　paper　introduces　the　Keepaway　Soccer　detailedly　and　compares　the　performances　of　two　RL　method-Q(λ)　and　Sarsa(λ).　The　reasons　why　they　perform　in　this　domain　are　explored　primarily.

关键词：

Magnetic domains Reinforcement learning Learning systems Learning algorithms

作者机构：

[ 1 ] [Han, Guang-Sheng]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 2 ] [Zhang, Hong-Wei]College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至