Knowledge Commons of Institute of Automation,CAS
Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics | |
Li, Hongliang; Liu, Derong; Wang, Ding | |
发表期刊 | IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING |
2014-07-01 | |
卷号 | 11期号:3页码:706-714 |
文章类型 | Article |
摘要 | In this paper, we develop an integral reinforcement learning algorithm based on policy iteration to learn online the Nash equilibrium solution for a two-player zero-sum differential game with completely unknown linear continuous-time dynamics. This algorithm is a fully model-free method solving the game algebraic Riccati equation forward in time. The developed algorithm updates value function, control and disturbance policies simultaneously. The convergence of the algorithm is demonstrated to be equivalent to Newton's method. To implement this algorithm, one critic network and two action networks are used to approximate the game value function, control and disturbance policies, respectively, and the least squares method is used to estimate the unknown parameters. The effectiveness of the developed scheme is demonstrated in the simulation by designing an H-infinity state feedback controller for a power system. |
关键词 | Adaptive Critic Designs Adaptive Dynamic Programming Approximate Dynamic Programming Reinforcement Learning Policy Iteration Zero-sum Games |
WOS标题词 | Science & Technology ; Technology |
关键词[WOS] | H-INFINITY CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; STATE-FEEDBACK CONTROL ; NONLINEAR-SYSTEMS ; PROGRAMMING ALGORITHM ; CONTROL SCHEME ; DESIGN ; ARCHITECTURE ; MANAGEMENT ; ITERATION |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Automation & Control Systems |
WOS类目 | Automation & Control Systems |
WOS记录号 | WOS:000340101400007 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/3832 |
专题 | 多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队 |
作者单位 | Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Hongliang,Liu, Derong,Wang, Ding. Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics[J]. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING,2014,11(3):706-714. |
APA | Li, Hongliang,Liu, Derong,&Wang, Ding.(2014).Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics.IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING,11(3),706-714. |
MLA | Li, Hongliang,et al."Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics".IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 11.3(2014):706-714. |
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-2014-TASE] Int(1753KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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