An Intersection Signal Control Method Based on Deep Reinforcement Learning

Urban traffic flow is dynamic and uncertain. In this paper, we combine the deep learning and the reinforcement learning, and design an intersection signal controller based on Q-learning and convolutional neural network. We redefine the state space and the reward function. The training and simulation of the controller are carried out in traffic micro-simulator SUMO. Compared with timing control, the results show that the method we have proposed is feasible and more effective.