An Agent-Based Simulation Modeling with Deep Reinforcement Learning for Smart Traffic Signal Control

The traffic congestion in a city is one of the most important problems that must be taken into account in the smart city. Many cities suffer from the serious traffic congestion as the city population and the number of vehicles increase. To solve the traffic problem, reinforcement learning based research works have been studied for training models for traffic signal control agents and have shown their performance through various traffic simulation. The reason is that it is significantly difficult to acquire traffic data directly from the real-world environments. To effectively model reinforcement learning-based traffic simulations, in this paper, we study a method for integrating deep reinforcement learning into traffic simulation modeling.