Quantitatively Evaluating Difficulty in Reaching Agreements in Multilateral Closed Negotiation Scenarios

Abstract

Negotiation is one type of these possible interactions through which intelligent agents can resolve their conflicts and maximize their utility. Furthermore, automated negotiation approaches are expected to greatly reduce the efforts that stakeholders have to expend during real-life negotiations. In this regard, we conceal the preference information of negotiation participants to protect privacy in a real-world negotiation environment. However, in such a negotiation environment, it is difficult for negotiation participants to search effective agreement candidates as reaching agreements. Therefore, in this study, we propose a metric called the Metric of Opposition Level (MOL), which is used for analyzing negotiation scenarios in an environment in which participants' preferences are concealed. The proposed metric MOL quantitatively indicates the difficulty in reaching an agreement by measuring how hostile the opponent agent is. In particular, a third person can analyze negotiation scenarios in consideration of the difficulty in negotiation participants searching agreement candidates. Experimental results indicate the impact of the MOL on agent negotiation results and its vital role in building better negotiation strategies.