一种递增叫价的多属性拍卖方法  

An Ascending Bid Multi-Attribute Auction Method

作　　者：金涬[1] 石纯一[1] 

机构地区：[1]清华大学计算机科学与技术系,北京100084

出　　处：《计算机研究与发展》2006年第7期1135-1141,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60373079;60496323)

摘　　要：采用拍卖方法来进行资源分配是多Agent系统研究中的重要问题.基于广义的多属性拍卖模型,提出了一种递增叫价的多属性拍卖方法——MAE.对MAE中卖方和买方的策略和效用进行了分析,进而证明了MAE的一些重要性质.例如卖方和买方满足独立理性,且都有接近最优的策略,在这一组策略下买方和卖方的总效用接近最大.将MAE与已有的多属性拍卖方法进行了比较,结果表明MAE改进了EstherDavid的工作,并且说明MAE是一种可以取代MAV的递增叫价多属性拍卖方法.Use auction methods to allocate resources among self-interested agents efficiently and reasonably is one of the challenges of multi-agent systems. Multi-attribute auctions extend traditional auction settings to allow negotiation over non-price attributes such as weight, color, size in addition to price. Based on a generalized multi-attribute auction model, an auction method-MAE is provided. MAE is an extension for English auction from single attribute to multi-attribute. Strategies and profits of buyer and sellers in MAE. Some main properties of MAE are proved. Buyers and sellers are individually rational in MAE. Buyers and sellers have nearly optimal strategies. The total profit of buyers and sellers is nearly optimal with the given strategies. Compared with Esther David＇s works, MAE has a more generalized model. Compared with the MAV auction, MAE is more transparent for sellers. Seller＇s strategy in MAE is more intuitive than in MAV.

关 键 词：多AGENT系统 多属性拍卖 叫价 卖方 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]