Close

Presentation

FedLight: Federated Reinforcement Learning for Autonomous Multi-Intersection Traffic Signal Control
Time
Location
Event Type
Research Manuscript
Virtual Programs
Hosted in Virtual Platform
Topics
Autonomous Systems
DescriptionAlthough Reinforcement Learning (RL) has been successfully applied in traffic control, it suffers from high average vehicle travel time and slow convergence to optimized solutions. To address this issue, this paper proposes a novel federated reinforcement learning approach named FedLight to enable optimal signal control policy generation for multi-intersection traffic scenarios. Inspired by federated learning, our approach supports knowledge sharing among RL agents, whose models are trained using decentralized traffic data at intersections. Experimental results show that our approach can not only achieve better average travel time for various multi-intersection configurations, but also converge to optimal solutions much faster.