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

TL;DR

This paper introduces a deep reinforcement learning algorithm for adaptive traffic signal control that automatically extracts features from raw data, significantly reducing vehicle delays compared to traditional methods.

Contribution

The paper presents a novel deep reinforcement learning approach with experience replay and target networks for traffic signal control using raw traffic data.

Findings

Reduces vehicle delay by up to 47% compared to longest queue first.

Achieves up to 86% delay reduction over fixed time control.

Demonstrates improved stability and effectiveness in simulation.

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.