Multi-Objective Decision Making in Collaborative Multi-Agent Systems




In collaborative multi-agent systems, teams of agents must coordinate their behavior in order to maximize their common utility.  Such systems are useful, not only for addressing tasks that are inherently distributed, but also for decomposing tasks that would otherwise be too complex to solve. Unfortunately, computing coordinated behavior is computationally expensive because the number of possible joint actions grows exponentially in the number of agents. Consequently, exploiting loose couplings between agents, as expressed in graphical models, is key to rendering such decision making efficient. However, existing methods for solving such models assume there is only a single objective. In contrast, many real-world problems are characterized by the presence of multiple objectives to which the solution is not a single action but the set of actions optimal for all trade-offs between the objectives. In this talk, I will propose a new method for multi-objective multi-agent graphical games that prunes away dominated solutions.  I will also discuss the theoretical support for this method and present an empirical study that shows that it can tackle multi-objective problems much faster than alternatives that do not exploit loose couplings.

Biography Shimon Whiteson:
Shimon is an assistant professor at the Informatics Institute at the University of Amsterdam, in the Intelligent Autonomous Systems group.  His research is primarily focused on single- and multi-agent decision-theoretic planning and learning, especially topics such as reinforcement learning, multi-agent planning and stochastic optimization methods like neuroevolution.

His current research efforts include best-match methods for reinforcement learning, multi-task reinforcement learning, balancing exploration and exploitation in information retrieval, neuroevolutionary helicopter control, analyzing novelty search, and optimally and approximately solving Dec-POMDPs.