Real-Time Driving Style Integration in Deep Reinforcement Learning for Traffic Signal Control

Most existing reinforcement learning-based traffic signal control approaches overlook vehicle-specific information in the state representation. This study addresses this gap by integrating real-time driving style information into the deep reinforcement learning (DRL) framework. We introduce a model-based framework that captures real-time driving styles and converts them into Intelligent Driver Model (IDM) parameters. Our proposed method demonstrates superior performance across various reinforcement algorithms and traffic flow scenarios, with statistical tests confirming a significant reduction in average queue length. The contributions of this paper can be summarized as follows: 1) proposing a model-based method for real-time driving style recognition, significantly reducing the requirements for trajectory data duration and computational resources, and 2) proposing a new state variable called transformed occupancy (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup>) that allows the DRL-based traffic signal controller to be trained with driving style information, thereby enhancing the performance of the traffic signal control system. The proposed framework is so flexible that other car-following models, machine learning algorithms, and various downstream tasks can be incorporated.