Regional Multi-Agent Cooperative Reinforcement Learning for City-Level Traffic Grid Signal ControlOACSTPCDEI

This article studies the effective traffic signal control problem of multiple intersections in a city-level traffic system.A novel regional multi-agent cooperative reinforcement learning algorithm called RegionSTLight is proposed to improve the traf-fic efficiency.Firstly a regional multi-agent Q-learning frame-work is proposed,which can equivalently decompose the global Q value of the traffic system into the local values of several regions.Based on the framework and the idea of human-machine cooper-ation,a dynamic zoning method is designed to divide the traffic network into several strong-coupled regions according to real-time traffic flow densities.In order to achieve better cooperation inside each region,a lightweight spatio-temporal fusion feature extraction network is designed.The experiments in synthetic,real-world and city-level scenarios show that the proposed RegionSTLight converges more quickly,is more stable,and obtains better asymptotic performance compared to state-of-the-art models.