The goal of this work is to provide a viable solution based on reinforcement learning for traffic signal control problems. Although the state-of-the-art reinforcement learning approaches have yielded great success in a variety of domains, directly applying it to alleviate traffic congestion can be challenging, considering the requirement of high sample efficiency and how training data is gathered. In this work, we address several challenges that we encountered when we attempted to mitigate serious traffic congestion occurring in a metropolitan area. Specifically, we are required to provide a solution that is able to (1) handle the traffic signal control when certain surveillance cameras that retrieve information for reinforcement learning are down, (2) learn from batch data without a traffic simulator, and (3) make control decisions without shared information across intersections. We present a two-stage framework to deal with the above-mentioned situations. The framework can be decomposed into an Evolution Strategies approach that gives a fixed-time traffic signal control schedule and a multi-agent off-policy reinforcement learning that is capable of learning from batch data with the aid of three proposed components, bounded action, batch augmentation, and surrogate reward clipping. Our experiments show that the proposed framework reduces traffic congestion by 36% in terms of waiting time compared with the currently used fixed-time traffic signal plan. Furthermore, the framework requires only 600 queries to a simulator to achieve the result.
ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Shanghai AI Laboratory（上海人工智能实验室）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；SenseTime Group Limited（商汤科技）
针对强化学习交通信号控制需按交叉口结构重新训练的问题，提出 ADLight，通过统一智能体设计与 movement shuffle 数据增强训练通用模型，在 SUMO 中以约5%等待时间代价节省逾80%训练时间。
GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
City University of Hong Kong（香港城市大学）；Jilin University（吉林大学）；Zhejiang University of Technology（浙江工业大学）；Southern University of Science and Technology（南方科技大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Alibaba Group（阿里巴巴集团）
LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
Alibaba Group（阿里巴巴集团）；The University of Hong Kong（香港大学）；Centre for Transformative Garment Production（变革性服装生产中心）；University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）
Bootstrap Your Own Latent（BYOL）是一种用于图像表示的自监督学习方法。从图像的增强视图，BYOL训练在线网络来预测同一图像的不同增强视图的目标网络表示。与对比方法不同，BYOL在其训练目标中没有明确使用由负对构建的排斥项。然而，它避免了崩溃到一个平凡的，恒定的表示。因此，最近有人假设，批量归一化（BN）是至关重要的，以防止崩溃BYOL。实际上，BN在批处理元素之间流动梯度，并且可能泄漏关于批处理中的否定视图的信息，这可能充当隐式否定（对比）项。然而，我们的实验表明，用独立于批次的标准化方案（即，组标准化和权重标准化的组合）取代BN，可以实现与vanilla BYOL相当的性能（$73.9\%$与$74.3\%$在ImageNet上使用ResNet- $50$的线性评估协议下的top-1准确度）。我们的发现反驳了使用批量统计是BYOL学习有用表示的关键因素的假设。
A Spatio-Temporal Online Robust Tensor Recovery Approach for Streaming Traffic Data Imputation
Center for Intelligent Decision-making and Machine Learning, School of Management, Xi’an Jiaotong University（智能决策与机器学习中心，管理学院，西安交通大学）；Department of Marketing, School of Management, Xi’an Jiaotong University（市场营销系，管理学院，西安交通大学）
MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
RelationMatch: Matching In-batch Relationships for Semi-supervised Learning
IIIS, Tsinghua University（清华大学智能产业研究院（注：IIIS为Institute for Interdisciplinary Information Sciences的缩写，常见译名为交叉信息研究院））；Department of Math, Tsinghua University（清华大学数学系）
Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Laboratory（中关村实验室）；School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）
Department of Statistics（统计学系）；The Pennsylvania State University（宾夕法尼亚州立大学）；Department of Applied and Computational Mathematics and Statistics（应用与计算数学与统计学系）；University of Notre Dame（圣母大学）
SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
Sungkyunkwan University（成均馆大学）；University of California, Riverside（加州大学河滨分校）；Center for Computational & Data Sciences, Independent University, Bangladesh（孟加拉国独立大学计算与数据科学中心）
ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis
Computer Science（计算机科学）；North Carolina A\&T State University（北卡罗来纳A&T州立大学）；Institute for Cyber Security（网络安全研究所）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
MNT-TNN: Spatiotemporal Traffic Data Imputation via Compact Multimode Nonlinear Transform-based Tensor Nuclear Norm
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences（智能机器研究所，合肥物理科学研究院，中国科学院）；University of Science and Technology of China（中国科学技术大学）
