Automatic negotiation: playing the domain instead of the opponent. Issue 3 (4th May 2017)

• Record Type: Journal Article
• Authors: Erez, Eden S.; Zuckerman, Inon; Hermel, Dror
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 29:Issue 3(2017)
• Page Start: 597
• Page End: 616
• Publication Date: 2017-05-04
• Subjects: Bargaining -- automated negotiations -- ANAC competition; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2016.1212102
• Languages: English
• ISSNs: 0952-813X

Abstract

Abstract : An automated negotiator is an intelligent agent whose task is to reach the best possible agreement. We explore a novel approach to developing a negotiation strategy, a 'domain-based approach'. Specifically, we use two domain parameters, reservation value and discount factor, to cluster the domain into different regions, in each of which we employ a heuristic strategy based on the notions of temporal flexibility and bargaining strength. Following the presentation of our cognitive and formal models, we show in an extensive experimental study that an agent based on that approach wins against the top agents of the automated negotiation competition of 2012 and 2013, and attained the second place in 2014.