模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (3): 223-231    DOI: 10.16451/j.cnki.issn1003-6059.202103004
Research on Reinforcement Learning Current Issue| Next Issue| Archive| Adv Search |
Emotion-Based Heterogeneous Multi-agent Reinforcement Learning with Sparse Reward
FANG Baofu1,2, MA Yunting1,2, WANG Zaijun3, WANG Hao1,2
1. School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601
2. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, Hefei University of Technology, Hefei, 230601
3. Key Laboratory of Flight Techniques and Flight Safety, Civil Aviation Flight University of China, Guanghan 618307

Download: PDF (1685 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  In reinforcement learning, the convergence speed and efficiency of the agent are greatly reduced due to its inability to acquire effective experience in an sparse reward distribution environment. Aiming at this kind of sparse reward problem, a method of emotion-based heterogeneous multi-agent reinforcement learning with sparse reward is proposed in this paper. Firstly, the emotion model based on personality is established to provide incentive mechanism for multiple heterogeneous agents as an effective supplement to external rewards. Then, based on this mechanism, a deep deterministic strategy gradient reinforcement learning algorithm based on intrinsic emotional incentive mechanism under sparse rewards is proposed to accelerate the convergence speed of agents. Finally, multi-robot pursuit is used as a simulation experiment platform to construct sparse reward scenarios with different difficulty levels, and the effectiveness and superiority of the proposed method in pursuit success rate and convergence speed are verified.
Key wordsReinforcement Learning      Sparse Reward      Reward Mechanism      Emotion Model     
Received: 27 November 2020     
ZTFLH: TP 391  
Fund:National Nature Science Foundation of China(No.61872327), Special Fund for Basic Scientific Research of Central Colleges(No.ACAIM190102), Open Fund of Key Laboratory of Flight Techniques and Flight Safety, CAAC(No.FZ2020KF07)
Corresponding Authors: FANG Baofu, Ph.D., associate professor. His research interests include multirobot/agent systems, emo-tion agent and reinforcement learning.   
About author:: MA Yunting, master student. Her research interests include computer application techno-logy, reinforcement learning and emotion agent.WANG Zaijun, master, associate profe-ssor. Her research interests include multi-robot task allocation and artificial intelligence.WANG Hao, Ph.D., professor. His research interests include artificial intelligence and robots.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
FANG Baofu
MA Yunting
WANG Zaijun
WANG Hao
Cite this article:   
FANG Baofu,MA Yunting,WANG Zaijun等. Emotion-Based Heterogeneous Multi-agent Reinforcement Learning with Sparse Reward[J]. , 2021, 34(3): 223-231.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202103004      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I3/223
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