FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks

doi:10.1109/TCYB.2016.2544866

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks
	Zhang, Zhen 1; Zhao, Dongbin2 ; Gao, Junwei 1; Wang, Dongqing 1; Dai, Yujie 3
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2017-06-01
卷号	47 期号:6 页码:1367-1379
文章类型	Article
摘要	In this paper, we propose a multiagent reinforcement learning algorithm dealing with fully cooperative tasks. The algorithm is called frequency of the maximum reward Q-learning (FMRQ). FMRQ aims to achieve one of the optimal Nash equilibria so as to optimize the performance index in multiagent systems. The frequency of obtaining the highest global immediate reward instead of immediate reward is used as the reinforcement signal. With FMRQ each agent does not need the observation of the other agents' actions and only shares its state and reward at each step. We validate FMRQ through case studies of repeated games: four cases of two-player two-action and one case of three-player two-action. It is demonstrated that FMRQ can converge to one of the optimal Nash equilibria in these cases. Moreover, comparison experiments on tasks with multiple states and finite steps are conducted. One is box-pushing and the other one is distributed sensor network problem. Experimental results show that the proposed algorithm outperforms others with higher performance.
关键词	Multiagent Reinforcement Learning (Marl) Nash Equilibrium Q-learning Repeated Game
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2016.2544866
关键词[WOS]	EVOLUTIONARY GAME-THEORY ; TRAFFIC SIGNAL CONTROL ; NETWORKS ; APPROXIMATION ; DESIGN
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61273136 ; Foundation of Shandong Province(ZR2015FM015 ; 61573353 ; ZR2015FM017) ; 61533017 ; 61573205)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000401950400002
引用统计	被引频次：52[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15124
专题	多模态人工智能系统全国重点实验室_深度强化学习
作者单位	1.Qingdao Univ, Coll Automat Engn, Qingdao 266071, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.China Acad Railway Sci, Transportat & Econ Inst, Beijing 100081, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Zhen,Zhao, Dongbin,Gao, Junwei,et al. FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks[J]. IEEE TRANSACTIONS ON CYBERNETICS,2017,47(6):1367-1379.
APA	Zhang, Zhen,Zhao, Dongbin,Gao, Junwei,Wang, Dongqing,&Dai, Yujie.(2017).FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks.IEEE TRANSACTIONS ON CYBERNETICS,47(6),1367-1379.
MLA	Zhang, Zhen,et al."FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks".IEEE TRANSACTIONS ON CYBERNETICS 47.6(2017):1367-1379.