arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00006cs.LGcs.AIcs.SYeess.SY
收藏

利用队列长度与注意力机制增强交通信号控制优化

Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization

State Key Laboratory of Herbage Improvement and Grassland Agro-ecosystems, College of Ecology, Lanzhou University（兰州大学生态学院、草种改良与草地农业生态系统国家重点实验室）

Liang Zhang, Shubin Xie, Jianming Deng

备注：
16 pages, 5 figures
发表信息：
"Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2023
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对交通信号控制中状态表示不足和相位关系依赖专家知识的问题，提出基于队列长度的M-QL传统优化方法和基于自注意力机制的AttentionLight强化学习模型，在多个真实数据集上验证了状态表示与网络设计同等重要并取得最优性能。

摘要：

近年来，用于交通信号控制（TSC）的强化学习（RL）技术越来越受欢迎。然而，现有基于RL的TSC方法大多主要关注RL模型结构，而忽视了恰当交通状态表示的重要性。此外，一些基于RL的方法严重依赖专家设计的交通信号相位竞争。在本文中，我们提出了一种利用队列长度作为高效状态表示的TSC新方法。我们提出了两种新方法：（1）Max Queue-Length（M-QL），一种基于队列长度性质设计的基于优化的传统方法；以及（2）AttentionLight，一种RL模型，采用自注意力机制捕捉信号相位相关性，无需人类提供相位关系知识。在多个真实世界数据集上的综合实验证明了我们方法的有效性：（1）M-QL方法优于最新的基于RL的方法；（2）AttentionLight取得了新的最先进性能；以及（3）我们的结果凸显了恰当状态表示的重要性，这在TSC方法中与神经网络设计同样关键。我们的发现对推动开发更有效和更高效的TSC方法具有重要意义。我们的代码已在Github上发布（https://github.com/LiangZhang1996/AttentionLight）。

英文摘要：

Reinforcement learning (RL) techniques for traffic signal control (TSC) have gained increasing popularity in recent years. However, most existing RL-based TSC methods tend to focus primarily on the RL model structure while neglecting the significance of proper traffic state representation. Furthermore, some RL-based methods heavily rely on expert-designed traffic signal phase competition. In this paper, we present a novel approach to TSC that utilizes queue length as an efficient state representation. We propose two new methods: (1) Max Queue-Length (M-QL), an optimization-based traditional method designed based on the property of queue length; and (2) AttentionLight, an RL model that employs the self-attention mechanism to capture the signal phase correlation without requiring human knowledge of phase relationships. Comprehensive experiments on multiple real-world datasets demonstrate the effectiveness of our approach: (1) the M-QL method outperforms the latest RL-based methods; (2) AttentionLight achieves a new state-of-the-art performance; and (3) our results highlight the significance of proper state representation, which is as crucial as neural network design in TSC methods. Our findings have important implications for advancing the development of more effective and efficient TSC methods. Our code is released on Github (https://github. com/LiangZhang1996/AttentionLight).

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑