Search algorithms for automated negotiation in large domains

Thimjo Koça, Dave de Jonge, Tim Baarslag

Abstract: This work presents several new and efficient algorithms that can be used by negotiating agents to explore very large outcome spaces. The proposed algorithms can search for bids close to a utility target or above a utility threshold, and for win-win outcomes. While doing so, these algorithms strike a careful balance between being rapid, accurate, diverse, and scalable, allowing agents to explore spaces with as many as \(10^{250}\) possible outcomes on very run-of-the-mill hardware. We show that our methods can be used to respond to the most common search queries employed by \(87\%\) of all agents from the Automated Negotiating Agents Competition between 2010 and 2021. Furthermore, we integrate our techniques into negotiation platform GeniusWeb in order to enable existing state-of-the-art agents (and future agents) to handle very large outcome spaces.