Abstract
Coordination is an important issue in multiagent systems. Within the stochastic game framework this problem translates to policy learning in a joint action space. This technique however suffers some important drawbacks like the assumption of the existence of a unique Nash equilibrium and synchronicity, the need for central control, the cost of communication, etc. Moreover in general sum games it is not always clear which policies should be learned. Playing pure Nash equilibrium is often unfair to at least one of the players, while playing a mixed strategy doesn’t give any guarantee for coordination and usually results in a sub-optimal payoff for all agents. In this work we show the usefulness of periodical policies, which arise as a side effect of the fairness conditions used by the agents. We are interested in games which assume competition between the players, but where the overall performance can only be as good as the performance of the poorest player. Players are social distributed reinforcement learners, who have to learn to equalize their payoff. Our approach is illustrated on synchronous one-step games as well as on asynchronous job scheduling games.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Claus C., Boutilier C.,: The dynamics of reinforcement learning in cooperative multi-agent systems. Proceedings of the fifteenth National Conference on Artificial Intelligence, (1998) p 746–752.
Gintis H.,: Game Theory Evolving: A Problem-Centered Introduction to Modeling Strategic Behavior. Princeton University Press, 2000.
Fehr E., Schmidt K.M.,: A Theory of Fairness, Competition, and Cooperation. Quarterly Journal of Economics, 114 (1999) p 817–868.
Hardin G.,: The tragedy of the commons. Science 162 (1968) p1243–1248.
Hu J., Wellman M. P.,: Multi Agent Reinforcement Learning in Stochastic Games. Submitted, 1999.
Litmann M.L.,: Markov games as a framework for multi-agent reinforcement learning. Proceedings of the Eleventh International Conference on Machine Learning, (1994) p 157–163.
Mariotti M.,: Maximum Games, Dominance Solvability, and Coordination. Games and Economic Behavior 31, (2000) p 97–105.
Narendra K., Thathachar M.,: Learning Automata: An Introduction. Prentice-Hall (1989).
Nowé, A., Verbeeck, K.,: Distributed Reinforcement learning, Loadbased Routing a case study. Proceedings of the Neural, Symbolic and Reinforcement Methods for sequence Learning Workshop at ijcai99.
Nowé, A., Verbeeck, K., Lenaerts T.,: Learning Agents in a Homo Egualis Society Technical report Computational Modeling Lab. Maart 2001. Vrije Uniuversiteit Brussel (2001).
Osborne J.O., Rubinstein A.,:A course in game theory. Cambridge, MA: MIT Press (1994).
Smith J.M.,: Evolution and the Theory of Games. Cambridge University Press (1982).
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction. Cambridge, MA: MIT Press (1998).
QNAP2 reference manual, SIMULOG 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nowé, A., Parent, J., Verbeeck, K. (2001). Social Agents Playing a Periodical Policy. In: De Raedt, L., Flach, P. (eds) Machine Learning: ECML 2001. ECML 2001. Lecture Notes in Computer Science(), vol 2167. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44795-4_33
Download citation
DOI: https://doi.org/10.1007/3-540-44795-4_33
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42536-6
Online ISBN: 978-3-540-44795-5
eBook Packages: Springer Book Archive