Abstract
A reinforcement learning-based dynamic congestion pricing method for morning commute problems is proposed. In this method, tolls are iteratively updated day by day based on observable information such as traffic volume. The advantage of the method is two fold. First, the method does not require travelers personal preferences such as value of time. Second, the method does not require manually designed toll update scheme; instead, the method automatically find the most efficient toll by a data-driven manner. Results of numerical experiments show that the proposed method properly decreased traffic congestion in various types of networks. Especially, in the experiment with a single bottleneck model, total waiting time decreases to nearly zero in about 200 days. One of future issues is more stable coordination among the time zones.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
