Large sequence models for sequential decision-making: a survey

doi:10.1007/s11704-023-2689-5

	Large sequence models for sequential decision-making: a survey
	Wen, Muning 1,2; Lin, Runji 3,4; Wang, Hanjing 1,2; Yang, Yaodong 5; Wen, Ying 1; Mai, Luo 6; Wang, Jun 2,7; Zhang, Haifeng 3,4; Zhang, Weinan 1
发表期刊	FRONTIERS OF COMPUTER SCIENCE
ISSN	2095-2228
	2023-12-01
卷号	17 期号:6 页码:18
通讯作者	Zhang, Weinan(wnzhang@sjtu.edu.cn)
摘要	Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally designed for prediction problems, it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems, which are typically beset by long-standing issues involving sample efficiency, credit assignment, and partial observability. In recent years, sequence models, especially the Transformer, have attracted increasing interest in the RL communities, spawning numerous approaches with notable effectiveness and generalizability. This survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with sequence models such as the Transformer, by discussing the connection between sequential decision-making and sequence modeling, and categorizing them based on the way they utilize the Transformer. Moreover, this paper puts forth various potential avenues for future research intending to improve the effectiveness of large sequence models for sequential decision-making, encompassing theoretical foundations, network architectures, algorithms, and efficient training systems.yy
关键词	sequential decision-making sequence modeling the Transformer training system
DOI	10.1007/s11704-023-2689-5
关键词[WOS]	REINFORCEMENT ; LEVEL
收录类别	SCI
语种	英语
资助项目	New Generation of AI 2030 Major Project[2018AAA0100900] ; Shanghai Municipal Science and Technology Major Project[2021SHZDZX0102] ; National Natural Science Foundation of China[62076161] ; Wu Wen Jun Honorary Scholarship, AI Institute, Shanghai Jiao Tong University
项目资助者	New Generation of AI 2030 Major Project ; Shanghai Municipal Science and Technology Major Project ; National Natural Science Foundation of China ; Wu Wen Jun Honorary Scholarship, AI Institute, Shanghai Jiao Tong University
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001042755200001
出版者	HIGHER EDUCATION PRESS
引用统计	被引频次：4[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/173211/53874
专题	复杂系统认知与决策实验室
通讯作者	Zhang, Weinan
作者单位	1.Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200241, Peoples R China 2.Digital Brain Lab, Shanghai 201306, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Peking Univ, Inst Artificial Intelligence, Beijing 100091, Peoples R China 6.Univ Edinburgh, Sch Informat, Edinburgh EH8 9JU, Scotland 7.UCL, Dept Comp Sci, London WC1E 6BT, England
推荐引用方式 GB/T 7714	Wen, Muning,Lin, Runji,Wang, Hanjing,et al. Large sequence models for sequential decision-making: a survey[J]. FRONTIERS OF COMPUTER SCIENCE,2023,17(6):18.
APA	Wen, Muning.,Lin, Runji.,Wang, Hanjing.,Yang, Yaodong.,Wen, Ying.,...&Zhang, Weinan.(2023).Large sequence models for sequential decision-making: a survey.FRONTIERS OF COMPUTER SCIENCE,17(6),18.
MLA	Wen, Muning,et al."Large sequence models for sequential decision-making: a survey".FRONTIERS OF COMPUTER SCIENCE 17.6(2023):18.