A MACHINE LEARNING APPROACH FOR MECHANISM SELECTION IN COMPLEX NEGOTIATIONS  

作　　者：Reyhan Aydogan Ivan Marsa-Maestre Mark Klein Catholijn M. Jonker 

机构地区：[1]Department of Computer Science, Ozyegin University, Istanbul, Turkey reyhan [2]Interactive Intelligence Group, Delft University of Technology, The Netherlands [3]Department of Computer Engineering, University of Alcala, 28805 Alcala de Henares, Madrid, Spain ivan [4]Interactive Center for Collective Intelligence, Massachusetts Institute of Technology, Cambridge, USA

出　　处：《Journal of Systems Science and Systems Engineering》2018年第2期134-155,共22页系统科学与系统工程学报（英文版）

摘　　要：Automated negotiation mechanisms can be helpful in contexts where users want to reach mutually satisfactory agreements about issues of shared interest, especially for complex problems with many interdependent issues. A variety of automated negotiation mechanisms have been proposed in the literature. The effectiveness of those mechanisms, however, may depend on the charaeteristics of the underlying negotiation problem （e.g. on the complexity of participant＇s utility functions, as well as the degree of conflict between participants）. While one mechanism may be a good choice for a negotiation problem, it may be a poor choice for another. In this paper, we pursue the problem of selecting the most effective negotiation mechanism given a particular problem by （1） defining a set of scenario metrics to capture the relevant features of negotiation problems, （2） evaluating the performance of a range of negotiation mechanisms on a diverse test suite of negotiation scenarios, （3） applying machine learning techniques to identify which mechanisms work best with which scenarios, and （4） demonstrating that using these classification rules for mechanism selection enables significantly better negotiation performance than any single mechanism alone.Automated negotiation mechanisms can be helpful in contexts where users want to reach mutually satisfactory agreements about issues of shared interest, especially for complex problems with many interdependent issues. A variety of automated negotiation mechanisms have been proposed in the literature. The effectiveness of those mechanisms, however, may depend on the charaeteristics of the underlying negotiation problem （e.g. on the complexity of participant＇s utility functions, as well as the degree of conflict between participants）. While one mechanism may be a good choice for a negotiation problem, it may be a poor choice for another. In this paper, we pursue the problem of selecting the most effective negotiation mechanism given a particular problem by （1） defining a set of scenario metrics to capture the relevant features of negotiation problems, （2） evaluating the performance of a range of negotiation mechanisms on a diverse test suite of negotiation scenarios, （3） applying machine learning techniques to identify which mechanisms work best with which scenarios, and （4） demonstrating that using these classification rules for mechanism selection enables significantly better negotiation performance than any single mechanism alone.

关 键 词：Automated negotiation mechanism selection scenario metrics 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP311[自动化与计算机技术—控制科学与工程]