Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network

Abstract

Adaptive traffic signal control, which adjusts traffic signal timing according to real-time traffic, has been shown to be an effective method to reduce traffic congestion. Available works on adaptive traffic signal control make responsive traffic signal control decisions based on human-crafted features (e.g. vehicle queue length). However, human-crafted features are abstractions of raw traffic data (e.g., position and speed of vehicles), which ignore some useful traffic information and lead to suboptimal traffic signal controls. In this paper, we propose a deep reinforcement learning algorithm that automatically extracts all useful features (machine-crafted features) from raw real-time traffic data and learns the optimal policy for adaptive traffic signal control. To improve algorithm stability, we adopt experience replay and target network mechanisms. Simulation results show that our algorithm reduces vehicle delay by up to 47% and 86% when compared to another two popular traffic signal control algorithms, longest queue first algorithm and fixed time control algorithm, respectively.

10 pages

References in corpus (2)

• Continuous control with deep reinforcement learning
• Using a Deep Reinforcement Learning Agent for Traffic Signal Control

Cited by in corpus (13)

• Real-time Cooperative Vehicle Coordination at Unsignalized Road Intersections
• Diagnosing Reinforcement Learning for Traffic Signal Control
• Advanced Traffic Management Systems: An Overview and A Development Strategy
• Deep Reinforcement Learning and Transportation Research: A Comprehensive Review
• A Transportation Digital-Twin Approach for Adaptive Traffic Control Systems
• Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning
• Finding Appropriate Traffic Regulations via Graph Convolutional Networks
• Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations
• A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
• Using AI for Mitigating the Impact of Network Delay in Cloud-based Intelligent Traffic Signal Control
• A Simple Traffic Signal Control Using Queue Length Information
• Optimal control of signalized intersection using hierarchical fuzzy-real control
• Decentralized Deep Reinforcement Learning for Network Level Traffic Signal Control