Overcoming Limitations of Game-Theoretic Distributed Control

Jason Marden
University of Colorado at Boulder

Friday, October 30, 2009 at 11:00am
Engr IV Room 57-124

Abstract
Game theory has recently received significant research attention as a tool for cooperative control of multi-agent systems. Utilizing game theory for cooperative control requires the following: (1) the interactions of a multi-agent distributed system are modeled as a non-cooperative game where the agents are designed as self-interested entities and (2) the agents are controlled using distributed learning algorithms that provide convergence to a stable operating point, e.g., Nash equilibrium. While there exists a large body of literature on distributed learning algorithms, unfortunately guidelines for how to design a "desirable" game are relatively unexplored. In this talk, we focus on the question of how to design agent objective functions. We demonstrate that the standard framework of non-cooperative game has inherent limitations with regard to designing agent objective functions. In particular, we prove that there does not exist a systematic method for constructing agent objective functions that are local, budget balanced and guarantee that the optimal control is a pure Nash equilibrium. However, we demonstrate that these limitations can be overcome by moving beyond the class of non-cooperative games and conditioning each player's objective function on additional information, i.e., a state.

Biography
Jason Marden's research interest is game theoretic methods for feedback control of distributed multi-agent systems. He received a BS in Mechanical Engineering in 2001 from UCLA, and a PhD in Mechanical Engineering in 2007, also from UCLA. Since 2007, he has been a junior fellow in the Social and Information Sciences Laboratory at the California Institute of Technology. This Spring he will be starting as an Assistant Professor in the Department of Electrical, Computer, and Energy Engineering at the University of Colorado at Boulder.