Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics
文献类型:期刊论文
作者 | Zhang, Qichao1,2; Zhao, Dongbin1,2 |
刊名 | IEEE TRANSACTIONS ON CYBERNETICS |
出版日期 | 2019-08-01 |
卷号 | 49期号:8页码:2874-2885 |
ISSN号 | 2168-2267 |
关键词 | Integral reinforcement learning (IRL) neural network (NN) nonzero-sum (NZS) games off-policy single-critic unknown drift dynamics |
DOI | 10.1109/TCYB.2018.2830820 |
英文摘要 | This paper is concerned about the nonlinear optimization problem of nonzero-sum (NZS) games with unknown drift dynamics. The data-based integral reinforcement learning (IRL) method is proposed to approximate the Nash equilibrium of NZS games iteratively. Furthermore, we prove that the data-based IRL method is equivalent to the model-based policy iteration algorithm, which guarantees the convergence of the proposed method. For the implementation purpose, a singl-ecritic neural network structure for the NZS games is given. To enhance the application capability of the data-based IRL method, we design the updating laws of critic weights based on the offline and online iterative learning methods, respectively. Note that the experience replay technique is introduced in the online iterative learning, which can improve the convergence rate of critic weights during the learning process. The uniform ultimate boundedness of the critic weights are guaranteed using the Lyapunov method. Finally, the numerical results demonstrate the effectiveness of the data-based M. algorithm for nonlinear NZS games with unknown drift dynamics. |
WOS关键词 | H-INFINITY CONTROL ; NONLINEAR-SYSTEMS ; ALGORITHM |
资助项目 | National Natural Science Foundation of China[61533017] ; National Natural Science Foundation of China[61573353] ; National Key Research and Development Plan[2016YFB0101000] |
WOS研究方向 | Automation & Control Systems ; Computer Science |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000467561700005 |
源URL | [http://ir.ia.ac.cn/handle/173211/24567] |
专题 | 复杂系统管理与控制国家重点实验室_深度强化学习 |
通讯作者 | Zhao, Dongbin |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Qichao,Zhao, Dongbin. Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics[J]. IEEE TRANSACTIONS ON CYBERNETICS,2019,49(8):2874-2885. |
APA | Zhang, Qichao,&Zhao, Dongbin.(2019).Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics.IEEE TRANSACTIONS ON CYBERNETICS,49(8),2874-2885. |
MLA | Zhang, Qichao,et al."Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics".IEEE TRANSACTIONS ON CYBERNETICS 49.8(2019):2874-2885. |
入库方式: OAI收割
来源:自动化研究所
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。