Co-evolutionary Agent Self-Organization for City Traffic Congestion Modeling

Luis Miramontes Hercog

Abstract. This paper introduces a model based on a multi-agent system that learns using the extended classifier system (MAXCS). The agents are informed in the news, after the weather forecast, the congestion levels of the main city avenues and they decide which avenue to use the following day. The results are encouraging, as the agents, both homogeneous and heterogeneous adapt to the congestion thresholds set by the authorities. The main factors for this adaptation are the reward received by the agents and their perception.

Keywords: Road traffic self-organization, Learning Classifier Systems, XCS, Emergent behavior, heterogeneous agents.

LNCS 3103, p. 993 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004