| 基于交互历史的多Agent自动协商研究 |
| |
| 引用本文： | 杨清平,蒲国林,王刚,邱玉辉.基于交互历史的多Agent自动协商研究[J].计算机科学,2008,35(9):226-229. |
| |
| 作者姓名： | 杨清平 蒲国林 王刚 邱玉辉 |
| |
| 作者单位： | 四川文理学院计算机科学系,达州635000;西南大学语义网格实验室,重庆400715;西南大学语义网格实验室,重庆,400715 |
| |
| 摘 要： | 在多Agent协商过程中,初始信念起到了至关重要的作用.而初始信念的形成是由设计者给予的部分专家知识和策略集,成功的交互历史是Agent在复杂环境中最后达成一致的提议集.通过学习机制从交互历史中获得知识,形成协商的初始信念,将更加有效地预测对方的策略,缩短协商过程的时间,再通过在线学习来协调己方Agent的行为.在此基础上优化协商模型,提高协商的效率和成功率.
|
| 关 键 词： | 多Agent 交互历史 协商 在线学习 |
Research on Multi-Agent Negotiation Based on Human-computer Interaction |
| |
| YANG Qing-ping,PU Guo-lin,WANG Gang,QIU Yu-hui.Research on Multi-Agent Negotiation Based on Human-computer Interaction[J].Computer Science,2008,35(9):226-229. |
| |
| Authors: | YANG Qing-ping PU Guo-lin WANG Gang QIU Yu-hui |
| |
| Affiliation: | YANG Qing-ping1,2 PU Guo-lin1,2 WANG Gang1 QIU Yu-hui1(Semantic Grid Laboratory,Southwest University,Chongqing 400715,China)1(Department of Computer Science,Sichuan University of Arts , Science,Dazhou 635000,China)2 |
| |
| Abstract: | Initial belief,the forming of which is the giving of partial expert knowledge and strategies integration by designers,plays an important role in the Multi-Agent negotiation.Successful human-computer interactive history,therefore,is unanimous offering set of multi-agent.In initial belief obtaining of knowledge forming negotiation by learning mechanism,the strategies of the other side can be forecasted effectively,and the time necessary for negotiation will be greatly shorten.Meanwhile,the acts of this side c... |
| |
| Keywords: | Multi-Agent Human-computer interaction history Negotiation On-line learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机科学》浏览原始摘要信息 |
|
点击此处可从《计算机科学》下载全文 |
|
