Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems
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);SenseTime Research(商汤科技研究院)
Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, Guoliang Fan
Asynchronous action coordination presents a pervasive challenge in Multi-Agent Systems (MAS), which can be represented as a Stackelberg game (SG). However, the scalability of existing Multi-Agent Reinforcement Learning (MARL) methods based on SG is severely constrained by network structures or environmental limitations. To address this issue, we propose the Stackelberg Decision Transformer (STEER), a heuristic approach that resolves the difficulties of hierarchical coordination among agents. STEER efficiently manages decision-making processes in both spatial and temporal contexts by incorporating the hierarchical decision structure of SG, the modeling capability of autoregressive sequence models, and the exploratory learning methodology of MARL. Our research contributes to the development of an effective and adaptable asynchronous action coordination method that can be widely applied to various task types and environmental configurations in MAS. Experimental results demonstrate that our method can converge to Stackelberg equilibrium solutions and outperforms other existing methods in complex scenarios.
AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering
University of Houston(休斯顿大学);New York University(纽约大学);Texas A&M University(德克萨斯农工大学);UCSD(加州大学圣地亚哥分校);Worcester Polytechnic Institute(伍斯特理工学院);Oregon State University(俄勒冈州立大学)
Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning
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)
针对多智能体同时行动难以形成均衡的问题,本文构建时空序贯决策结构,并用共享条件超网络实现 N 级 Stackelberg 策略学习,在矩阵博弈、合作与混合任务中验证了有效性。
Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks
School of Automation, Guangdong University of Technology(广东工业大学自动化学院);School of Navigation, Wuhan University of Technology(武汉理工大学导航学院);Department of Software Engineering, College of Computer and Information Sciences, King Saud University(沙特国王大学软件工程系)
Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning
Siemens Technology and Services Pvt. Ltd.(西门子技术服务私人有限公司);International Institute of Information Technology Hyderabad(海得拉巴国际信息技术学院);Indian Institute of Science Bengaluru(班加罗尔印度科学研究所)
Stackelberg POMDP: Learning to Lead via Reinforcement Learning
OpenAI;Bryant University(布莱恩特大学);Hebrew University of Jerusalem(耶路撒冷希伯来大学);Columbia University(哥伦比亚大学);Google(谷歌);Adaptive Innovations;Partnership on AI(人工智能伙伴关系);Brown University(布朗大学);Harvard University(哈佛大学)