Abstract
In evolutionary game theory, one is normally interested in the investigation about how the distribution of strategies changes along time. Equilibrium-based methods are not appropriate for open, dynamic systems, as for instance those in which individual drivers learn to select routes. In this paper we model route choice in which many agents adapt simultaneously. We investigate the dynamics with a continuous method (replicator dynamics), and with learning methods (social and individual). We show how the convergence to one of the Nash equilibria depends on the underlying learning dynamics selected, as well as on the pace of adjustments by the driver agents.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Wardrop, J.G.: Some theoretical aspects of road traffic research. Proceedings of the Institute of Civil Engineers 1, 325–362 (1952)
Koutsoupias, E., Papadimitriou, C.: Worst-case equilibria. In: Meinel, C., Tison, S. (eds.) STACS 1999. LNCS, vol. 1563, pp. 404–413. Springer, Heidelberg (1999)
Papadimitriou, C.H.: Algorithms, games, and the internet. In: Proc. of the 33rd ACM Symp. on Theory of Computing (STOC), pp. 749–753. ACM Press (2001)
Roughgarden, T., Tardos, É.: How bad is selfish routing? J. ACM 49, 236–259 (2002)
Braess, D.: Über ein Paradoxon aus der Verkehrsplanung. Unternehmensforschung 12, 258 (1968)
Fudenberg, D., Levine, D.K.: The Theory of Learning in Games. The MIT Press (1998)
Börgers, T., Sarin, R.: Learning through reinforcement and replicator dynamics. Journal of Economic Theory 77, 1–14 (1997)
Tuyls, K., Hoen, P.J., Vanschoenwinkel, B.: An evolutionary dynamical analysis of multi-agent learning in iterated games. Autonomous Agents and Multiagent Systems 12, 115–153 (2006)
Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746–752 (1998)
Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems 11, 387–434 (2005)
Shoham, Y., Powers, R., Grenager, T.: If multi-agent learning is the answer, what is the question? Artificial Intelligence 171, 365–377 (2007)
Webb, J.N.: Game Theory – Decisions, Interaction and Evolution. Springer, London (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bazzan, A.L.C. (2013). Paying the Price of Learning Independently in Route Choice. In: Correia, L., Reis, L.P., Cascalho, J. (eds) Progress in Artificial Intelligence. EPIA 2013. Lecture Notes in Computer Science(), vol 8154. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40669-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-40669-0_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40668-3
Online ISBN: 978-3-642-40669-0
eBook Packages: Computer ScienceComputer Science (R0)