In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach, named c-MBA. Our proposed formulation can craft much stronger adversarial state perturbations of c-MARL agents to lower total team rewards than existing model-free approaches. In addition, we propose the first victim-agent selection strategy and the first data-driven approach to define targeted failure states where each of them allows us to develop even stronger adversarial attack without the expert knowledge to the underlying environment. Our numerical experiments on two representative MARL benchmarks illustrate the advantage of our approach over other baselines: our model-based attack consistently outperforms other baselines in all tested environments.
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Institute of Data Space, Hefei Comprehensive National Science Center（合肥综合性国家科学中心数据空间研究院）；Institute of Artificial Intelligence, Peking University（北京大学人工智能研究院）；Nanyang Technological University（南洋理工大学）
MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library
ReLER, AAII, University of Technology Sydney（悉尼科技大学）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能工程学院）；Shandong Artificial Intelligence Institute, Qilu University of Technology（齐鲁工业大学山东省人工智能研究院）
Efficiently Quantifying Individual Agent Importance in Cooperative MARL
InstaDeep Ltd（InstaDeep有限公司）；National School of Computer Science, Tunisia（突尼斯国家计算机科学学校）；National School of Engineering of Tunis（突尼斯国家工程学院）；University of Edinburgh（爱丁堡大学）
From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Scalable and Reliable Multi-agent Reinforcement Learning for Traffic Assignment
Department of Data Science and Artificial Intelligence, Monash University（数据科学与人工智能系，墨尔本大学）；Chair of Transportation Systems Engineering, Technical University of Munich（交通系统工程主任，慕尼黑技术大学）；School of Transportation, Southeast University（交通学院，东南大学）；The Graduate School of Informatics and Engineering, The University of Electro-Communications（信息与工程研究生院，电通大学）；Department of Civil Engineering, Monash University（土木工程系，墨尔本大学）；Department of Civil and Architectural Engineering, KTH Royal Institute of Technology（土木与建筑工程系，皇家理工技术学院）
TimeGNN-Augmented Hybrid-Action MARL for Fine-Grained Task Partitioning and Energy-Aware Offloading in MEC
College of Computer and Mathematics（计算机与数学学院）；Central South University of Forestry and Technology（林业与技术中央南大学）；Department of Computer Science（计算机科学系）；State University of New York（纽约州立大学）
Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging
Department of Automation, Tsinghua University（自动化系，清华大学）；Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University（北京信息科学与技术国家研究中心（BNRist），清华大学）
Heterogeneity in Multi-Agent Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；National Key Laboratory of Cognition and Decision Intelligence for Complex Systems（复杂系统认知与决策智能国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Settling the Variance of Multi-Agent Policy Gradients
Imperial College London（帝国理工学院）；Huawei R&D UK（华为英国研发中心）；Shanghai Jiao Tong University（上海交通大学）；Institute of Automation, Chinese Academy of Science（中国科学院自动化研究所）；University College London（伦敦大学学院）；Institute for AI, Peking University（北京大学人工智能研究院）
M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
Department of Informatics, King’s College London, London, United Kingdom（伦敦大学国王学院信息学系）；Societal Systems Department, Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学社会系统系）
LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
School of Automation Science and Electrical Engineering, Beihang University（自动化科学与电气工程学院，北京航空航天大学）；WINDY Lab, Department of Artificial Intelligence, Westlake University（WINDY实验室，人工智能学院，西湖大学）
Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning Services
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Shenzhen CyberAray Network Technology Co., Ltd, China（深圳 CyberAray 网络技术有限公司）；Information and Communication Branch of State Grid Hebei Electric Power Co., Ltd, China（国网河北电力信息通信分部）；Zhejiang Lab as well as Zhejiang University（浙江实验室以及浙江大学）
HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
MOX – Department of Mathematics, Politecnico di Milano（数学系，米兰理工学院）；Department of Mechanical Engineering, Politecnico di Milano（机械工程系，米兰理工学院）；Department of Aeronautics, Imperial College London（航空系，伦敦帝国学院）
