作　　者： ; ;

机构地区： 华南理工大学计算机科学与工程学院

出　　处： 《华南理工大学学报（自然科学版）》 2007年第9期95-100,共6页

摘　　要： 针对双边多议题协商中的僵局问题,提出利用并发Options优化协商模型的方法.这种方法可在不降低双边协商效用的前提下,并行动态优化与僵局议题相关的多个议题的保留值.电子商务的实验结果表明:基于并发Options的协商模型优化方法是有效的;无论是学习速度,还是最佳策略的优化程度和泛化能力,该方法均明显优于基于标准Options和Q-学习的优化方法. 　In order to break the deadlocks in the bilateral and multi-issue negotiation,a method to optimize the negotiation model is proposed based on concurrent Options.In this method,the reserved values of several issues rela-ted to the deadlock issue can be dynamically optimized in parallel without reducing the bilateral utility.As illustrated by an example of E-commerce,the proposed optimization method is effective.It significantly outperforms the methods based on standard Options and Q-learning in terms of the learning efficiency as well as the optimization degree and generalization capacity of the learned policies for solving negotiation deadlocks.

关 键 词： 协商模型 协商僵局 优化 并发 强化学习

领　　域： [自动化与计算机技术] [自动化与计算机技术]