The Important Role of Global State for Multi-Agent Reinforcement Learning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 空间自动化技术研究室

	The Important Role of Global State for Multi-Agent Reinforcement Learning
	Li SL(李帅龙)2,3,5; Zhang W(张伟)2,3; Leng YQ(冷雨泉)1,4; Wang XH(王晓辉)2,3,5
刊名	Future Internet
	2022
卷号	14 期号:1 页码:1-9
关键词	multi-agent reinforcement learning environmental information deep reinforcement learning
ISSN号	1999-5903
产权排序	1
英文摘要	Environmental information plays an important role in deep reinforcement learning (DRL). However, many algorithms do not pay much attention to environmental information. In multi-agent reinforcement learning decision-making, because agents need to make decisions combined with the information of other agents in the environment, this makes the environmental information more important. To prove the importance of environmental information, we added environmental information to the algorithm. We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. The average score of our algorithm was higher than that of the original algorithm (except for VDN and COMA), which shows that our work significantly outperforms existing multi-agent RL methods.
语种	英语
资助机构	National Natural Science Foundation of China under Grant 52175272, 51805237 ; Joint Fund of Science & Technology Department of Liaoning Province ; State Key Laboratory of Robotics, China (Grant No.2020-KF-22-03)
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/30296]
专题	沈阳自动化研究所_空间自动化技术研究室
通讯作者	Zhang W(张伟)
作者单位	1.Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 4.Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China 5.University of Chinese Academy of Sciences, Beijing 100049, China
推荐引用方式 GB/T 7714	Li SL,Zhang W,Leng YQ,et al. The Important Role of Global State for Multi-Agent Reinforcement Learning[J]. Future Internet,2022,14(1):1-9.
APA	Li SL,Zhang W,Leng YQ,&Wang XH.(2022).The Important Role of Global State for Multi-Agent Reinforcement Learning.Future Internet,14(1),1-9.
MLA	Li SL,et al."The Important Role of Global State for Multi-Agent Reinforcement Learning".Future Internet 14.1(2022):1-9.