The benefits of opponent models in negotiation

Koen Hindriks*, Catholijn M. Jonker, Dmytro Tykhonov

*Corresponding author for this work

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Information about the opponent is essential to improve automated negotiation strategies for bilateral multi-issue negotiation. In this paper we propose a negotiation strategy that exploits a technique to learn a model of opponent preferences in a single negotiation session. An opponent model may be used to achieve at least two important goals in negotiation. First, it can be used to recognize, avoid and respond appropriately to exploitation, which differentiates the strategy proposed from commonly used concession-based strategies. Second, it can be used to increase the efficiency of a negotiated agreement by searching for Pareto-optimal bids. A negotiation strategy should be efficient, transparent, maximize the chance of an agreement and should avoid exploitation. We argue that the proposed strategy satisfies these criteria and analyze its performance experimentally.

Original languageEnglish
Title of host publicationProceedings - 2009 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2009
Pages439-444
Number of pages6
Volume2
DOIs
Publication statusPublished - 1 Dec 2009
Externally publishedYes
Event2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2009 - Milano, Italy
Duration: 15 Sep 200918 Sep 2009

Conference

Conference2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2009
Country/TerritoryItaly
CityMilano
Period15/09/0918/09/09

Keywords

  • Bayesian learning; negotiation strategy
  • Multi-issue negotiation
  • Opponent modelling
  • Tit-for-Tat

Cite this