Traffic signal control can mitigate traffic congestion and reduce travel time. A model-free reinforcement learning (RL) approach is a powerful framework for learning a responsive traffic control policy for short-term traffic demand changes without prior environmental knowledge. Previous RL approaches could handle high-dimensional feature space using a standard neural network, e.g., a convolutional neural network; however, to control traffic on a road network with multiple intersections, the geometric features between roads had to be created manually. Rather than using manually crafted geometric features, we developed an RL-based traffic signal control method that employs a graph convolutional neural network (GCNN). GCNNs can automatically extract features considering the traffic features between distant roads by stacking multiple neural network layers. We numerically evaluated the proposed method in a six-intersection environment. The results demonstrate that the proposed method can find comparable policies twice as fast as the conventional RL method with a neural network and can adapt to more extensive traffic demand changes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Signal Control Based on Reinforcement Learning with Graph Convolutional Neural Nets


    Contributors:


    Publication date :

    2018-11-01


    Size :

    1085778 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Reinforcement learning-based traffic signal control

    Sheng, Liu Tian / Azman, Afizan Bin / Khan, Navid Ali et al. | IEEE | 2024


    Self-adaptive traffic signal control method based on graph deep reinforcement learning

    ZHAO ZHONGNAN / WANG KUN / SONG XIN | European Patent Office | 2022

    Free access

    Graph convolutional neural network and reinforcement learning fused highland cooperative control method

    LIANG ZHAN / WANG CHONG / ZHANG YUNYI | European Patent Office | 2025

    Free access