Saved in:
Bibliographic Details
Main Authors: Zhang, Liang, Zhang, Yutong, Deng, Jianming, Li, Chen
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.10828
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913338402799616
author Zhang, Liang
Zhang, Yutong
Deng, Jianming
Li, Chen
author_facet Zhang, Liang
Zhang, Yutong
Deng, Jianming
Li, Chen
contents Reinforcement learning (RL) has emerged as a promising solution for addressing traffic signal control (TSC) challenges. While most RL-based TSC systems typically employ an online approach, facilitating frequent active interaction with the environment, learning such strategies in the real world is impractical due to safety and risk concerns. To tackle these challenges, this study introduces an innovative offline data-driven approach, called DataLight. DataLight employs effective state representations and reward function by capturing vehicular speed information within the environment. It then segments roads to capture spatial information and further enhances the spatially segmented state representations with sequential modeling. The experimental results demonstrate the effectiveness of DataLight, showcasing superior performance compared to both state-of-the-art online and offline TSC methods. Additionally, DataLight exhibits robust learning capabilities concerning real-world deployment issues. The code is available at https://github.com/LiangZhang1996/DataLight.
format Preprint
id arxiv_https___arxiv_org_abs_2303_10828
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle DataLight: Offline Data-Driven Traffic Signal Control
Zhang, Liang
Zhang, Yutong
Deng, Jianming
Li, Chen
Machine Learning
Artificial Intelligence
Reinforcement learning (RL) has emerged as a promising solution for addressing traffic signal control (TSC) challenges. While most RL-based TSC systems typically employ an online approach, facilitating frequent active interaction with the environment, learning such strategies in the real world is impractical due to safety and risk concerns. To tackle these challenges, this study introduces an innovative offline data-driven approach, called DataLight. DataLight employs effective state representations and reward function by capturing vehicular speed information within the environment. It then segments roads to capture spatial information and further enhances the spatially segmented state representations with sequential modeling. The experimental results demonstrate the effectiveness of DataLight, showcasing superior performance compared to both state-of-the-art online and offline TSC methods. Additionally, DataLight exhibits robust learning capabilities concerning real-world deployment issues. The code is available at https://github.com/LiangZhang1996/DataLight.
title DataLight: Offline Data-Driven Traffic Signal Control
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2303.10828