模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (10): 851-872    DOI: 10.16451/j.cnki.issn1003-6059.202410001
Surveys and Reviews Current Issue| Next Issue| Archive| Adv Search |
A Review of Multi-agent Reinforcement Learning Theory and Applications
CHEN Zhuoran1, LIU Zeyang1, WAN Lipeng1, CHEN Xingyu1, ZHU Yameng2, WANG Chengze2, CHENG Xiang3, ZHANG Ya4, ZHANG Senlin5, WANG Xiaohui6, LAN Xuguang1
1. Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an 710049;
2. China Academy of Launch Vehicle Technology, Beijing 100076;
3. School of Electronics, Peking University, Beijing 100871;
4. School of Automation, Southeast University, Nanjing 210096;
5. College of Electrical Engineering, Zhejiang University, Hangzhou 310027;
6. Artificial Intelligence Research Institute, China Electric Power Research Institute, Beijing 100192

Download: PDF (1775 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Reinforcement learning(RL) is a widely utilized machine learning paradigm for addressing sequential decision-making problems. Its core principle involves enabling agents to learn optimal policies iteratively through feedback derived from interactions between an agent and the environment. As the demands for computational power and data scale of practical applications continue to escalate, the transition from single-agent intelligence to collective intelligence becomes an inevitable trend in the future development of artificial intelligence. Therefore, challenges and opportunities are abundant for RL. In this paper, grounded on the concept of deep multi-agent reinforcement learning(MARL), the current theoretical dilemmas are refined and analyzed, including limited scalability, credit assignment, exploration-exploitation dilemma, non-stationarity and partial observability of information. Various solutions and their advantages and disadvantages proposed by researchers are elaborated. Typical training and learning environment of MARL and its practical applications in complex decision-making fields, such as smart city construction, gaming, robotics control and autonomous driving, are introduced. The challenges and future development direction of collaborative multi-agent reinforcement learning are summarized.
Key wordsDeep Reinforcement Learning      Multi-agent      Credit Assignment      Human Feedback      Markov Decision Process     
Received: 30 September 2024     
ZTFLH: TP 181  
Fund:National Key Research and Development Program of China(No.2021ZD0112700), National Natural Science Foun-dation of China(No.62125305,62088102,U23A20339,62203348)
Corresponding Authors: LAN Xuguang, Ph.D., professor. His research interests include computer vision and machine learning.   
About author:: CHEN Zhuoran, Ph.D. candidate. His research interests include deep reinforcement learning. LIU Zeyang, Ph.D., assistant professor. His research interests include deep reinforcement learning. WAN Lipeng, Ph.D., assistant professor. His research interests include deep reinforcement learning and coexisting-cooperative-cognitive robots. CHEN Xingyu, Ph.D., assistant profe-ssor. His research interests include computer vision and machine learning. ZHU Yameng, Master, engineer. Her research interests include game theory and autonomous control of agents. WANG Chengze, Master student. His research interests include game theory and autonomous control of agents. CHENG Xiang, Ph.D., professor. His research interests include data-driven intelligence network and networked intelligence. ZHANG Ya, Ph.D., professor. Her research interests include multi-agent game theory and reinforcement learning. Zhang Senlin, Master, professor. His research interests include control theory and its applications. WANG Xiaohui, Ph.D., senior engineer. His research interests include electric power artificial intelligence, electric power systems and automation.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHEN Zhuoran
LIU Zeyang
WAN Lipeng
CHEN Xingyu
ZHU Yameng
WANG Chengze
CHENG Xiang
ZHANG Ya
ZHANG Senlin
WANG Xiaohui
LAN Xuguang
Cite this article:   
CHEN Zhuoran,LIU Zeyang,WAN Lipeng等. A Review of Multi-agent Reinforcement Learning Theory and Applications[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(10): 851-872.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202410001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I10/851
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn