Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems | |
Luo, Biao1; Liu, Derong2; Huang, Tingwen4; Yang, Xiong3; Ma, Hongwen1 | |
刊名 | INFORMATION SCIENCES |
2017-10-01 | |
卷号 | 411期号:0页码:66-83 |
关键词 | Optimal Control Multi-step Heuristic Dynamic Programming Adaptive Dynamic Programming Nonlinear Systems Discrete-time Neural Networks |
DOI | 10.1016/j.ins.2017.05.005 |
文献子类 | Article |
英文摘要 | Policy iteration and value iteration are two main iterative adaptive dynamic programming frameworks for solving optimal control problems. Policy iteration converges fast while requiring an initial stabilizing control policy, which is a strict constraint in practice. Value iteration avoids the requirement of initial admissible control policy while converging much slowly. This paper tries to utilize the advantages of policy iteration and value iteration, and avoids their drawbacks at the same time. Therefore, a multi-step heuristic dynamic programming (MsHDP) method is developed for solving the optimal control problem of nonlinear discrete-time systems. MsHDP speeds up value iteration and avoids the requirement of initial admissible control policy in policy iteration at the same time. The convergence theory of MsHDP is established by proving that it converges to the solution of the Bellman equation. For implementation purpose, the actor-critic neural network (NN) structure is developed. The critic NN is employed to estimate the value function and its NN weight vector is computed with a least-square scheme. The actor NN is used to estimate the control policy and a gradient descent method is proposed for updating its NN weight vector. According to the comparative simulation studies on two examples, the effectiveness and advantages of MsHDP are verified. (C) 2017 Elsevier Inc. All rights reserved. |
WOS关键词 | Spatially Distributed Processes ; Optimal Tracking Control ; Horizon Optimal-control ; Neural-network Control ; Optimal-control Scheme ; H-infinity Control ; Policy Iteration ; Control Design ; Feedback-control ; Algorithm |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000404197200005 |
资助机构 | National Natural Science Foundation of China(61533017 ; Early Career Development Award of SKLMCCS ; NPRP from the Qatar National Research Fund (a member of Qatar Foundation)(NPRP 9 166-1-031) ; U1501251 ; 61374105 ; 61503377 ; 61233001) |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/15245] |
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.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Guangdong, Peoples R China 3.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China 4.Texas A&M Univ Qatar, POB 23874, Doha, Qatar |
推荐引用方式 GB/T 7714 | Luo, Biao,Liu, Derong,Huang, Tingwen,et al. Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems[J]. INFORMATION SCIENCES,2017,411(0):66-83. |
APA | Luo, Biao,Liu, Derong,Huang, Tingwen,Yang, Xiong,&Ma, Hongwen.(2017).Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems.INFORMATION SCIENCES,411(0),66-83. |
MLA | Luo, Biao,et al."Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems".INFORMATION SCIENCES 411.0(2017):66-83. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论