An Enhanced Dueling Double Deep Q-Network With Convolutional Block Attention Module for Traffic Signal Optimization in Deep Reinforcement Learning

An Enhanced Dueling Double Deep Q-Network With Convolutional Block Attention Module for Traffic Signal Optimization in Deep Reinforcement Learning

Many studies on the application of deep reinforcement learning (DRL) in the field of traffic signal control do not fully consider the influence of vehicles approaching the intersection on traffic flow. In this paper, the convolutional block attention module (CBAM) is incorporated on the basis of the...

Full description

Bibliographic Details
Main Authors: Peng Wang, Wenlong Ni
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Attention mechanism
deep reinforcement learning
deep Q network
traffic signal control
Online Access:https://ieeexplore.ieee.org/document/10477432/

Internet

https://ieeexplore.ieee.org/document/10477432/

Similar Items