Abstract

Automated negotiation among self-interested autonomous agents has gained tremendous attention due to the diversity of its broad range of potential real-world applications. This article deals with a prominent type of such negotiations, namely, multiissue negotiation that runs under continuous-time constraints and in which the negotiating agents have no prior knowledge about their opponents ’ preferences and strategies. A negotiation strategy called Dragon is described that employs sparse pseudoinput Gaussian processes. Specifically, Dragon enables an agent (1) to precisely model the behavior of its opponents with compara-bly low computational load and (2) to make decisions effectively and adaptively in very complex negotiation settings. Extensive experimental results, based on a number of negotiation scenarios and state-of-the-art ne-gotiating agents from Automated Negotiating Agents Competitions, are provided. Moreover, the robustness of our strategy is evaluated through both empirical game-theoretic and spatial evolutionary game-theoretic analysis.