Advanced State-Aware Traffic Light Optimization Control with Deep Q-Network

The former traffic light control (TLC) system cannot effectively regulate the traffic conditions dynamically in real time due to urban growth. The Dueling Double Deep Recurrent Q-Network with Attention Mechanism (3DRQN-AM) method for TLC is proposed in this study. The proposed method is based on Deep Q-Network and employs target network, double learning method and dueling network to boost its learning efficiency. In order to integrate the past state of the vehicle’s motion trajectory with the current state of the vehicle for the best decision-making, the Long-Short Term Memory (LSTM) is introduced. While this is going on, an Attention Mechanism is introduced to help the neural network automatically focus on crucial state components and improve its capacity to represent state. According to experimental findings, the Dueling Double Deep Q-Network with Attention Mechanism (3DQN-AM), Dueling Double Deep Recurrent Q-Network (3DRQN), Dueling Double Deep Q-Network (3DQN), Fixed-Time-3DRQN-AM (FT-3DRQN-AM) signal management methods are compared. The techniques presented in this work lower the average waiting time under typical traffic flow by about 46.2%, 53.3%, 85.1%, and 30.0% respectively, and the average queue length by about 41.9%, 44.6%, 76.0%, and 21.7% respectively. Under peak traffic conditions, the average waiting time is decreased by around 20.8%, 32.1%, 36.7%, and 38.7% respectively, while the average queue is decreased by roughly 2.8%, 2.8%, 21.3%, and 44.9%.