Abstract—For traffic signal control of intersections in cities, a
new controller based on reinforcement learning and fuzzy
neural network is proposed in this paper. The fuzzy neural
network has the advantages of both fuzzy control and neural
network, and overcome the former’s lack of self-learning and
generalization ability, and the latter’s lack of understandability.
Meanwhile, the reinforcement learning can make the controller
improve itself on line continually by the simple feedback of
environment. The result of computational experiments shows
that the proposed traffic signal control algorithm can achieve a
more effective optimization control.