Field Deployment of Multi-Agent Reinforcement Learning Based Variable Speed Limit Controllers

TL;DR

This paper reports the first real-world deployment of a multi-agent reinforcement learning system for variable speed limit control on a major highway, demonstrating its effectiveness and robustness in live traffic management.

Contribution

It introduces a practical framework for training MARL agents in simulation and deploying them directly in real-world traffic control, including safety measures and domain mismatch analysis.

Findings

System made 10 million decisions on 8 million trips

MARL policy controlled up to 98% of traffic without safety guard intervention

Algorithm adapts during rush hours and shows robustness to simulation-reality mismatch

Abstract

This article presents the first field deployment of a multi-agent reinforcement-learning (MARL) based variable speed limit (VSL) control system on the I-24 freeway near Nashville, Tennessee. We describe how we train MARL agents in a traffic simulator and directly deploy the simulation-based policy on a 17-mile stretch of Interstate 24 with 67 VSL controllers. We use invalid action masking and several safety guards to ensure the posted speed limits satisfy the real-world constraints from the traffic management center and the Tennessee Department of Transportation. Since the time of launch of the system through April, 2024, the system has made approximately 10,000,000 decisions on 8,000,000 trips. The analysis of the controller shows that the MARL policy takes control for up to 98% of the time without intervention from safety guards. The time-space diagrams of traffic speed and control commands illustrate how the algorithm behaves during rush hour. Finally, we quantify the domain mismatch between the simulation and real-world data and demonstrate the robustness of the MARL policy to this mismatch.