Research on parameters of reinforcement learning on multi-agent system - 文章详情页

作者：

Zuo, Guoyu (Zuo, Guoyu.) (学者：左国玉) | Zhang, Hongwei (Zhang, Hongwei.) | Han, Guangsheng (Han, Guangsheng.) | Li, Jia (Li, Jia.)

收录：

EI Scopus

摘要：

Reinforcement　learning(RL)　has　been　applied　on　the　testbed　of　keepaway,　a　typical　multi-agent　system.　To　get　the　best　performances　of　RL　and　figure　out　what　influence　the　learning　speed　and　the　finally　results,　different　values　of　the　important　variables　had　been　selected　in　the　emulator.　The　results　intimated　the　influence　of　each　parameter　to　the　course　of　learning,　and　established　the　base　of　exploring　the　better　values　of　parameters.　This　paper　is　also　good　for　the　researches　on　the　effective　solution　to　the　problems　of　huge　state　spaces.　©　2008　IEEE.

关键词：

Football Intelligent agents Learning systems Multi agent systems Reinforcement learning

作者机构：

[ 1 ] [Zuo, Guoyu]Beijing University of Technology, Beijing 100022, China
[ 2 ] [Zhang, Hongwei]Beijing University of Technology, Beijing 100022, China
[ 3 ] [Han, Guangsheng]Beijing University of Technology, Beijing 100022, China
[ 4 ] [Li, Jia]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