Abstract. Offer generation is an important mechanism in automated negotiation, in which a negotiating agent needs to select bids close to the opponent preference to increase their chance of being accepted. The existing offer generation approaches are either random, require partial knowledge of opponent preference or are domain-dependent. In this paper, we investigate and compare two vector similarity functions for generating offer vectors close to opponent preference. Vector similarities are not domain-specific, do not require different similarity functions for each negotiation domain and can be computed in incomplete-information negotiation. We evaluate negotiation outcomes by the joint gain obtained by the agents and by their closeness to Pareto-optimal solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.