Manifold Regularized Reinforcement Learning
Li, Hongliang1; Liu, Derong2; Wang, Ding3
2018-04-01
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
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
DOI10.1109/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:2[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
专题复杂系统管理与控制国家重点实验室_平行控制
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.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Hongliang]的文章
[Liu, Derong]的文章
[Wang, Ding]的文章
百度学术
百度学术中相似的文章
[Li, Hongliang]的文章
[Liu, Derong]的文章
[Wang, Ding]的文章
必应学术
必应学术中相似的文章
[Li, Hongliang]的文章
[Liu, Derong]的文章
[Wang, Ding]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。