Mixture of personality improved spiking actor network for efficient multi-agent cooperation

doi:10.3389/fnins.2023.1219405

	Mixture of personality improved spiking actor network for efficient multi-agent cooperation
	Li, Xiyun1,2 ; Ni, Ziyi 1,3; Ruan, Jingqing 1,2; Meng, Linghui 1,3; Shi, Jing1,3 ; Zhang, Tielin1,3 ; Xu, Bo1,2,3,4
发表期刊	FRONTIERS IN NEUROSCIENCE
	2023-07-06
卷号	17 页码:14
通讯作者	Zhang, Tielin(tielin.zhang@ia.ac.cn) ; Xu, Bo(xubo@ia.ac.cn)
摘要	Adaptive multi-agent cooperation with especially unseen partners is becoming more challenging in multi-agent reinforcement learning (MARL) research, whereby conventional deep-learning-based algorithms suffer from the poor new-player-generalization problem, possibly caused by not considering theory-of-mind theory (ToM). Inspired by the ToM personality in cognitive psychology, where a human can easily resolve this problem by predicting others' intuitive personality first before complex actions, we propose a biologically-plausible algorithm named the mixture of personality (MoP) improved spiking actor network (SAN). The MoP module contains a determinantal point process to simulate the formation and integration of different personality types, and the SAN module contains spiking neurons for efficient reinforcement learning. The experimental results on the benchmark cooperative overcooked task showed that the proposed MoP-SAN algorithm could achieve higher performance for the paradigms with (learning) and without (generalization) unseen partners. Furthermore, ablation experiments highlighted the contribution of MoP in SAN learning, and some visualization analysis explained why the proposed algorithm is superior to some counterpart deep actor networks.
关键词	multi-agent cooperation personality theory spiking actor networks multi-agent reinforcement learning theory of mind
DOI	10.3389/fnins.2023.1219405
关键词[WOS]	GO
收录类别	SCI
语种	英语
WOS研究方向	Neurosciences & Neurology
WOS类目	Neurosciences
WOS记录号	WOS:001029486500001
出版者	FRONTIERS MEDIA SA
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53706
专题	复杂系统认知与决策实验室
通讯作者	Zhang, Tielin; Xu, Bo
作者单位	1.Chinese Acad Sci, Inst Automat, Lab Cognit & Decis Intelligence Complex Syst, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Li, Xiyun,Ni, Ziyi,Ruan, Jingqing,et al. Mixture of personality improved spiking actor network for efficient multi-agent cooperation[J]. FRONTIERS IN NEUROSCIENCE,2023,17:14.
APA	Li, Xiyun.,Ni, Ziyi.,Ruan, Jingqing.,Meng, Linghui.,Shi, Jing.,...&Xu, Bo.(2023).Mixture of personality improved spiking actor network for efficient multi-agent cooperation.FRONTIERS IN NEUROSCIENCE,17,14.
MLA	Li, Xiyun,et al."Mixture of personality improved spiking actor network for efficient multi-agent cooperation".FRONTIERS IN NEUROSCIENCE 17(2023):14.