Reference
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.
Abstract
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.
Downloads
BibTeX
@techreport{BabBus:06-041,
author = {Babu{\v{s}}ka, Robert and Bu{\c{s}}oniu, Lucian and De
Schutter, Bart},
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}
}