CASIA OpenIR  > 深度强化学习团队
Event-triggered integral reinforcement learning for nonlinear continuous-time systems
Qichao Zhang1,2; Dongbin Zhao
2017
Conference NameIEEE Symposium Series on Computational Intelligence (SSCI)
Conference DateNov. 27 to Dec 1, 2017
Conference PlaceHonolulu, Hawaii, USA
Abstract

In this paper, the optimal control problem for the continuous-time nonlinear systems with partially unknown dynamics is investigated. The event-triggered internal reinforcement learning (IRL) is proposed to approach the solution of the Hamilton-Jacobi-Bellman (HJB) equation. Note that the knowledge of internal dynamics is relaxed, and the event-triggered control scheme is adopted to reduce the computational burden and communication resources. For the online implementation purpose, a single-critic neural network (NN) structure is constructed to approach the optimal value function and the optimal policy with convergence analysis. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed algorithm.

MOST Discipline Catalogue工学
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26139
Collection深度强化学习团队
Affiliation1.Institute of Automation, CAS
2.University of Chinese Academy of Sciences, CAS
Recommended Citation
GB/T 7714
Qichao Zhang,Dongbin Zhao. Event-triggered integral reinforcement learning for nonlinear continuous-time systems[C],2017.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qichao Zhang]'s Articles
[Dongbin Zhao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qichao Zhang]'s Articles
[Dongbin Zhao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qichao Zhang]'s Articles
[Dongbin Zhao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.