Manifold Regularized Reinforcement Learning

doi:10.1109/TNNLS.2017.2650943

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 复杂系统智能机理与平行控制团队

	Manifold Regularized Reinforcement Learning
	Li, Hongliang 1; Liu, Derong 2; Wang, Ding3
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2018-04-01
卷号	29 期号:4 页码:932-943
文章类型	Article
摘要	This paper introduces a novel manifold regularized reinforcement learning scheme for continuous Markov decision processes. Smooth feature representations for value function approximation can be automatically learned using the unsupervised manifold regularization method. The learned features are data-driven, and can be adapted to the geometry of the state space. Furthermore, the scheme provides a direct basis representation extension for novel samples during policy learning and control. The performance of the proposed scheme is evaluated on two benchmark control tasks, i.e., the inverted pendulum and the energy storage problem. Simulation results illustrate the concepts of the proposed scheme and show that it can obtain excellent performance.
关键词	Adaptive Dynamic Programming Approximate Dynamic Programming Approximate Policy Iteration (Api) Manifold Regularization Reinforcement Learning (Rl)
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2017.2650943
关键词[WOS]	TIME NONLINEAR-SYSTEMS ; VALUE FUNCTION APPROXIMATION ; SQUARES POLICY ITERATION ; DIMENSIONALITY REDUCTION ; LAPLACIAN FRAMEWORK ; GEOMETRIC FRAMEWORK ; ALGORITHMS ; REPRESENTATION ; MACHINES ; DESIGN
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000427859600014
引用统计	被引频次：18[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/173211/21992
专题	多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
作者单位	1.Tencent Inc, AI Platform Dept, Shenzhen 518057, Peoples R China 2.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Hongliang,Liu, Derong,Wang, Ding. Manifold Regularized Reinforcement Learning[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(4):932-943.
APA	Li, Hongliang,Liu, Derong,&Wang, Ding.(2018).Manifold Regularized Reinforcement Learning.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(4),932-943.
MLA	Li, Hongliang,et al."Manifold Regularized Reinforcement Learning".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.4(2018):932-943.