一个基于Agent的轿车市场自动协商模型

该文提出了一个针对轿车市场中交易协商的双边多议题自动协商模型，该模型具有如下特点：用基于效用的相似度比较法实现Agent智能搜索；模型采用学习机制包括历史学习和Q-学习，历史学习机制用于Agent协商前初始信念的创建，对Agent在协商中策略的选择、执行具有指导作用。Q-学习机制用于生成协商提议，使得Agent能够在半竞争、信息不完全和不确定以及存在最大协商时间的情况下，更为有效地完成多议题协商。

An Agent-based Automated Negotiation Model in Car Market

This paper develops a bilateral multi-issue negotiation model in car market.The characteristic of this model is as follows: intelligent-agent searching,with A utility-based similarity compare method; learning mechanism including history learning and Q-learning ,the former is used to update of the initial beliefs of the Agent before negotiation,and plays a guidable role in selecting and implementing the tactics in Agent negotiation,the latter can propose own proposal and enable the multi-issue negotiation more effective in semi-competitive situation in which there exists information uncertainty and deadlines.