Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems
Liu, Derong; Li, Hongliang; Wang, Ding
2015-06-01
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷号26期号:6页码:1323-1334
文章类型Article
摘要In this paper, we establish error bounds of adaptive dynamic programming algorithms for solving undiscounted infinite-horizon optimal control problems of discrete-time deterministic nonlinear systems. We consider approximation errors in the update equations of both value function and control policy. We utilize a new assumption instead of the contraction assumption in discounted optimal control problems. We establish the error bounds for approximate value iteration based on a new error condition. Furthermore, we also establish the error bounds for approximate policy iteration and approximate optimistic policy iteration algorithms. It is shown that the iterative approximate value function can converge to a finite neighborhood of the optimal value function under some conditions. To implement the developed algorithms, critic and action neural networks are used to approximate the value function and control policy, respectively. Finally, a simulation example is given to demonstrate the effectiveness of the developed algorithms.
关键词Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Neural Networks Neurodynamic Programming Nonlinear Systems Optimal Control
WOS标题词Science & Technology ; Technology
关键词[WOS]TIME NONLINEAR-SYSTEMS ; MARKOV DECISION-PROCESSES ; OPTIMAL TRACKING CONTROL ; ZERO-SUM GAMES ; POLICY ITERATION ; LAPLACIAN FRAMEWORK ; UNKNOWN DYNAMICS ; FEEDBACK-CONTROL ; CONTROL SCHEME ; HJB SOLUTION
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:000354957000017
引用统计
被引频次:23[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/173211/7924
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
Liu, Derong,Li, Hongliang,Wang, Ding. Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2015,26(6):1323-1334.
APA Liu, Derong,Li, Hongliang,&Wang, Ding.(2015).Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,26(6),1323-1334.
MLA Liu, Derong,et al."Error Bounds of Adaptive Dynamic Programming Algorithms for Solving Undiscounted Optimal Control Problems".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 26.6(2015):1323-1334.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
[00-J-2015-TNNLS] Er(1114KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Liu, Derong]的文章
[Li, Hongliang]的文章
[Wang, Ding]的文章
百度学术
百度学术中相似的文章
[Liu, Derong]的文章
[Li, Hongliang]的文章
[Wang, Ding]的文章
必应学术
必应学术中相似的文章
[Liu, Derong]的文章
[Li, Hongliang]的文章
[Wang, Ding]的文章
相关权益政策
暂无数据
收藏/分享
文件名: [00-J-2015-TNNLS] Error bounds of adaptive dynamic programming algorithms for solving undiscounted optimal control problems.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。