Traffic signal timing via deep reinforcement learning

TLDR

The paper proposes algorithms that use deep reinforcement learning to design traffic signal timing plans. The method trains a deep neural network to approximate the Q‑function from traffic states and performance, then derives signal timing policies by modeling control actions and state transitions. The authors discuss the benefits, implementation tricks, and how the approach relates to existing methods.

Abstract

In this paper, we propose a set of algorithms to design signal timing plans via deep reinforcement learning. The core idea of this approach is to set up a deep neural network (DNN) to learn the Q-function of reinforcement learning from the sampled traffic state/control inputs and the corresponding traffic system performance output. Based on the obtained DNN, we can find the appropriate signal timing policies by implicitly modeling the control actions and the change of system states. We explain the possible benefits and implementation tricks of this new approach. The relationships between this new approach and some existing approaches are also carefully discussed.