MAS-Soccer: a testbed based on multi-agent cooperation | |
Zhang Shuangmin ; Shi Chunyi | |
2010-05-06 ; 2010-05-06 | |
关键词 | Practical/ feature extraction learning (artificial intelligence) mobile robots multi-agent systems multi-robot systems/ MAS-Soccer multi-agent cooperation reinforcement learning algorithms feature vector extraction Q-learning algorithm Robocup/ C3390C Mobile robots C6170K Knowledge engineering techniques |
中文摘要 | A testbed is needed to test and compare various multi-agent cooperative problem solving algorithms. A multi-agent cooperative simulation system based on BDI reasoning, MAS-Soccer, was developed to emphasize the importance of joint strategies in multi-agent systems, rather than the performance details of specific actions. The system can be used to test reinforcement learning algorithms based on feature vector extraction and the traditional Q-learning algorithm in the Robocup free kick game. Tests illustrate the efficiency of the system and that MAS-Soccer can efficiently and correctly compare various cooperative strategies. |
语种 | 英语 ; 英语 |
出版者 | Tsinghua Univ. Press ; China |
内容类型 | 期刊论文 |
源URL | [http://hdl.handle.net/123456789/10060] |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | Zhang Shuangmin,Shi Chunyi. MAS-Soccer: a testbed based on multi-agent cooperation[J],2010, 2010. |
APA | Zhang Shuangmin,&Shi Chunyi.(2010).MAS-Soccer: a testbed based on multi-agent cooperation.. |
MLA | Zhang Shuangmin,et al."MAS-Soccer: a testbed based on multi-agent cooperation".(2010). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论