Bayesian Critique-Tune-Based Reinforcement Learning with Attention-Based Adaptive Pressure for Multi-Intersection Traffic Signal Control

Adaptive Traffic Signal Control (ATSC) system is a critical component of intelligent transportation, with the capability to significantly alleviate urban traffic congestion. Although reinforcement learning (RL)-based methods have demonstrated promising performance in achieving ATSC, existing methods find it prone to convergence to local optima. Consequently, this paper proposes a novel Bayesian Critique-Tune-Based Reinforcement Learning with Attention-Based Adaptive Pressure (BCT-APRL) for multi-intersection signal control. In BCT-APRL, the Critique-Tune (CT) framework, a two-layer Bayesian structure is designed to refine the RL policies. Specifically, the Bayesian inference-based Critique layer provides effective evaluations of the credibility of policies; the Bayesian decision-based Tune layer fine-tunes policies by minimizing the posterior risks when the evaluations are negative. Furthermore, an attention-based Adaptive Pressure (AP) is designed to specify the traffic movement representation as an effective and efficient pressure of vehicle queues in the traffic network. Achieving enhances the reasonableness of RL policies. Extensive experiments conducted with a simulator across a range of intersection layouts show that BCT-APRL is superior to other state-of-the-art methods in seven real-world datasets. Codes are open-sourced.