Reinforcement learning for multi-agent systems

R. Babuška, L. Buşoniu, and B. De Schutter, "Reinforcement learning for multi-agent systems," Tech. report 06-041, Delft Center for Systems and Control, Delft University of Technology, 7 pp., July 2006. Paper for a keynote presentation at the 11th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2006), Prague, Czech Republic, Sept. 2006.

Multi-agent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, etc. Although the individual agents can be programmed in advance, many tasks require that they learn behaviors online. A significant part of the research on multi-agent learning concerns reinforcement learning techniques. This paper gives a survey of multi-agent reinforcement learning, starting with a review of the different viewpoints on the learning goal, which is a central issue in the field. Two generic goals are distinguished: stability of the learning dynamics, and adaptation to the other agents' dynamic behavior. The focus on one of these goals, or a combination of both, leads to a categorization of the methods and approaches in the field. The challenges and benefits of multi-agent reinforcement learning are outlined along with open issues and future research directions.

Technical report: pdf file (308 KB)

@techreport{BabBus:06-041,
author={R. Babu{\v{s}}ka and L. Bu{\c{s}}oniu and B. {D}e Schutter},
title={Reinforcement learning for multi-agent systems},
number={06-041},
institution={Delft Center for Systems and Control, Delft University of Technology},
month=jul,
year={2006},
note={Paper for a keynote presentation at the \emph{11th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA~2006)}, Prague, Czech Republic, Sept.\ 2006}
}

Go to the publications overview page.

This page is maintained by Bart De Schutter. Last update: March 1, 2025.