Abstract
Graph neural network combined with reinforcement learning is one of the most effective traffic signal control methods. However, existing methods fail to pay enough attention to the key information, such as the traffic information of the downstream section in extracting state and the intersection’s own state in aggregating information from neighbor intersections. As a result, adverse reactions like unstable learning and limited performance occur frequently when agents and models focus on interfering information and useless information too much. In this article, we propose KeyLight, an intelligent traffic signal control method based on reinforcement learning by facilitating the attention of the learning algorithm and model to the key information that is usually ignored. In KeyLight, we design a new state representation NOV-LADLE and introduce residual connection in the graph neural network to highlight the importance of the intersection’s state. Experiments show that, in the case of comparable throughput, the proposed KeyLight has been greatly improved and enhanced in performance. Especially, the average travel time can be increased by up to 23.44% on the real-world dataset.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.