Supply Chain Management World: A Benchmark Environment for Situated Negotiations

Abstract

In the very near future, we anticipate that more and more artificially intelligent agents will be deployed to represent individuals and institutions. Automated negotiation environments are a mechanism by which to coordinate the behavior of such agents. Most existing work on automated negotiation assumes a context that is predefined, and hence, static. This paper focuses on the dynamic case, which we call situated negotiation, where agents need to decide not only how to negotiate, but with whom, and about what. We describe a common benchmark simulation environment for evaluating situated negotiation strategies, and evaluate several baseline strategies in the proposed environment.