Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics
文献类型：期刊论文
| 作者 | Zhao, Dongbin ; Zhang, Qichao; Wang, Ding; Zhu, Yuanheng
|
| 刊名 | IEEE TRANSACTIONS ON CYBERNETICS
 |
| 出版日期 | 2016-03-01 |
| 卷号 | 46期号:3页码:854-865 |
| 关键词 | Adaptive Dynamic Programming (Adp) Experience Replay Nonzero-sum (Nzs) Games Optimal Control Unknown Dynamics |
| DOI | 10.1109/TCYB.2015.2488680 |
| 文献子类 | Article |
| 英文摘要 | In this paper, an approximate online equilibrium solution is developed for an N-player nonzero-sum (NZS) game systems with completely unknown dynamics. First, a model identifier based on a three-layer neural network (NN) is established to reconstruct the unknown NZS games systems. Moreover, the identifier weight vector is updated based on experience replay technique which can relax the traditional persistence of excitation condition to a simplified condition on recorded data. Then, the single-network adaptive dynamic programming (ADP) with experience replay algorithm is proposed for each player to solve the coupled nonlinear Hamilton-Jacobi (HJ) equations, where only the critic NN weight vectors are required to tune for each player. The feedback Nash equilibrium is provided by the solution of the coupled HJ equations. Based on the experience replay technique, a novel critic NN weights tuning law is proposed to guarantee the stability of the closed-loop system and the convergence of the value functions. Furthermore, a Lyapunov-based stability analysis shows that the uniform ultimate boundedness of the closed-loop system is achieved. Finally, two simulation examples are given to verify the effectiveness of the proposed control scheme. |
| WOS关键词 | TIME NONLINEAR-SYSTEMS ; DIFFERENTIAL-GAMES ; ALGORITHM ; NETWORKS |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000370963500023 |
| 资助机构 | National Natural Science Foundation of China(61273136 ; 61573353 ; 61533017 ; 61304086) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11349]  |
| 专题 | 复杂系统管理与控制国家重点实验室_深度强化学习 |
| 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 | Zhao, Dongbin,Zhang, Qichao,Wang, Ding,et al. Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(3):854-865. |
| APA | Zhao, Dongbin,Zhang, Qichao,Wang, Ding,&Zhu, Yuanheng.(2016).Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics.IEEE TRANSACTIONS ON CYBERNETICS,46(3),854-865. |
| MLA | Zhao, Dongbin,et al."Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics".IEEE TRANSACTIONS ON CYBERNETICS 46.3(2016):854-865. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。