Penina Hoz-Weiss, Bar-Ilan University; Sarit Kraus, Bar-Ilan University and University of Maryland; Jonathan Wilkenfeld and Tara E. Santmire, University of Maryland
We present an automated agent that can negotiate efficiently with humans in bilateral negotiations with time constraints, deadlines, full information, and the possibility of opting out. The negotiation is conducted using a semi-formal language. The model used in constructing the agent is based on a formal analysis of the scenario using game theoretic methods and heuristics for argumentation. The agent receives messages sent by humans, analyzes them and responds. It also initiates discussion on one or more parameters of an agreement. The specific scenario concerns a crisis between Spain and Canada over access to a fishery. The human players are provided with a DSS to analyze the scenario and compare the utility points associated with various outcomes, and with a language editor to facilitate the composition of messages.