An adaptive traffic signal control scheme with Proximal Policy Optimization based on deep reinforcement learning for a single intersection

Adaptive traffic signal control (ATSC) is an important means to alleviate traffic congestion and improve the quality of road traffic. Although deep reinforcement learning (DRL) technology has shown great potential in solving traffic signal control problems, the state representation and reward design, as well as action interval time, still need to be further studied. The advantages of policy learning have not been fully applied in TSC. To address the aforementioned issues, we propose a DRL-based traffic signal control scheme with Poximal Policy Optimization (PPO-TSC). We use the waiting time of vehicles and the queue length of lanes represented the spatiotemporal characteristics of traffic flow to design the simplified traffic states feature vectors, and define the reward function that is consistent with the state. Additionally, we compare and analyze the performance indexes obtained by various methods using action intervals of 5s, 10s, and 15s. The algorithm is implemented based on the Actor-Critic architecture, using the advantage estimation and the clip mechanism to constrain the range of gradient updates. We validate the proposed scheme at a single intersection in Simulation of Urban MObility (SUMO) under two different traffic demand patterns of flat traffic and peak traffic. The experimental results show that the proposed method is significantly better than other compared methods. Specifically, PPOTSC demonstrates a reduction of 24% in average travel time (ATT), a decrease of 45% in the average time loss (ATL), and an increase of 16% in average speed (AS) compared with the existing methods under peak traffic condition.