Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning
This addresses traffic congestion in urban networks by improving efficiency, though it is incremental as it extends existing methods to a larger scale.
The study tackled large-scale mixed traffic control by using decentralized multi-agent reinforcement learning to manage intersections with both traffic signals and robot vehicles, resulting in a reduction of average waiting time from 6.17s to 5.09s and an increase in throughput from 454 to 493 vehicles per 500 seconds at 80% RV penetration rate.
Traffic congestion remains a significant challenge in modern urban networks. Autonomous driving technologies have emerged as a potential solution. Among traffic control methods, reinforcement learning has shown superior performance over traffic signals in various scenarios. However, prior research has largely focused on small-scale networks or isolated intersections, leaving large-scale mixed traffic control largely unexplored. This study presents the first attempt to use decentralized multi-agent reinforcement learning for large-scale mixed traffic control in which some intersections are managed by traffic signals and others by robot vehicles. Evaluating a real-world network in Colorado Springs, CO, USA with 14 intersections, we measure traffic efficiency via average waiting time of vehicles at intersections and the number of vehicles reaching their destinations within a time window (i.e., throughput). At 80% RV penetration rate, our method reduces waiting time from 6.17s to 5.09s and increases throughput from 454 vehicles per 500 seconds to 493 vehicles per 500 seconds, outperforming the baseline of fully signalized intersections. These findings suggest that integrating reinforcement learning-based control large-scale traffic can improve overall efficiency and may inform future urban planning strategies.