CSpace
Model-Free Reinforcement Learning by Embedding an Auxiliary System for Optimal Control of Nonlinear Systems
Xu, Zhenhui1; Shen, Tielong1; Cheng, Daizhan2
2022-04-01
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
卷号33期号:4页码:1520-1534
摘要In this article, a novel integral reinforcement learning (IRL) algorithm is proposed to solve the optimal control problem for continuous-time nonlinear systems with unknown dynamics. The main challenging issue in learning is how to reject the oscillation caused by the externally added probing noise. This article challenges the issue by embedding an auxiliary trajectory that is designed as an exciting signal to learn the optimal solution. First, the auxiliary trajectory is used to decompose the state trajectory of the controlled system. Then, by using the decoupled trajectories, a model-free policy iteration (PI) algorithm is developed, where the policy evaluation step and the policy improvement step are alternated until convergence to the optimal solution. It is noted that an appropriate external input is introduced at the policy improvement step to eliminate the requirement of the input-to-state dynamics. Finally, the algorithm is implemented on the actor-critic structure. The output weights of the critic neural network (NN) and the actor NN are updated sequentially by the least-squares methods. The convergence of the algorithm and the stability of the closed-loop system are guaranteed. Two examples are given to show the effectiveness of the proposed algorithm.
关键词Mathematical model Trajectory Heuristic algorithms Optimal control System dynamics Artificial neural networks Convergence Approximate optimal control design auxiliary trajectory completely model-free integral reinforcement learning (IRL)
DOI10.1109/TNNLS.2020.3042589
收录类别SCI
语种英语
资助项目JSPS KAKENHI[17H03284]
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:000778930100016
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型期刊论文
条目标识符http://ir.amss.ac.cn/handle/2S8OKBNM/60286
专题中国科学院数学与系统科学研究院
通讯作者Xu, Zhenhui
作者单位1.Sophia Univ, Dept Engn & Appl Sci, Tokyo 1028554, Japan
2.Chinese Acad Sci, Acad Math & Syst Sci, Key Lab Syst & Control, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Xu, Zhenhui,Shen, Tielong,Cheng, Daizhan. Model-Free Reinforcement Learning by Embedding an Auxiliary System for Optimal Control of Nonlinear Systems[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022,33(4):1520-1534.
APA Xu, Zhenhui,Shen, Tielong,&Cheng, Daizhan.(2022).Model-Free Reinforcement Learning by Embedding an Auxiliary System for Optimal Control of Nonlinear Systems.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,33(4),1520-1534.
MLA Xu, Zhenhui,et al."Model-Free Reinforcement Learning by Embedding an Auxiliary System for Optimal Control of Nonlinear Systems".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 33.4(2022):1520-1534.
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
[Xu, Zhenhui]的文章
[Shen, Tielong]的文章
[Cheng, Daizhan]的文章
百度学术
百度学术中相似的文章
[Xu, Zhenhui]的文章
[Shen, Tielong]的文章
[Cheng, Daizhan]的文章
必应学术
必应学术中相似的文章
[Xu, Zhenhui]的文章
[Shen, Tielong]的文章
[Cheng, Daizhan]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。