CASIA OpenIR

Browse/Search Results:  1-10 of 13 Help

Filters    
Selected(0)Clear Items/Page:    Sort:
A novel neural optimal control framework with nonlinear dynamics: Closed-loop stability and simulation verification 期刊论文
NEUROCOMPUTING, 2017, 卷号: 266, 页码: 353-360
Authors:  Wang, Ding;  Mu, Chaoxu
Adobe PDF(1503Kb)  |  Favorite  |  View/Download:56/5  |  Submit date:2018/03/03
Adaptive Dynamic Programming  Adaptive System  Learning Control  Neural Network  Optimal Regulator  Stability  
Adaptive total-variation for non-negative matrix factorization on manifold 期刊论文
PATTERN RECOGNITION LETTERS, 2017, 卷号: 98, 页码: 68-74
Authors:  Leng, Chengcai;  Cai, Guorong;  Yu, Dongdong;  Wang, Zongyue
Favorite  |  View/Download:45/0  |  Submit date:2018/03/03
Adaptive Total Variation  Non-negative Matrix Factorization  Manifold Learning  
Improving the Critic Learning for Event-Based Nonlinear H-infinity Control Design 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 卷号: 47, 期号: 10, 页码: 3417-3428
Authors:  Wang, Ding;  He, Haibo;  Liu, Derong
Adobe PDF(1068Kb)  |  Favorite  |  View/Download:65/11  |  Submit date:2018/03/03
H-infinity Control  Adaptive Systems  Adaptive/approximate Dynamic Programming  Critic Network  Event-based Design  Learning Criterion  Neural Control  
Adaptive Critic Nonlinear Robust Control: A Survey 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 卷号: 47, 期号: 10, 页码: 3429-3451
Authors:  Wang, Ding;  He, Haibo;  Liu, Derong
Adobe PDF(1954Kb)  |  Favorite  |  View/Download:79/23  |  Submit date:2018/03/03
Adaptive Critic Designs  Adaptive/approximate Dynamic Programming (Adp)  Boundedness  Convergence  Neural Networks  Optimal Control  Reinforcement Learning  Robust Control  Stability  
Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 卷号: 47, 期号: 10, 页码: 3341-3354
Authors:  Luo, Biao;  Liu, Derong;  Wu, Huai-Ning;  Wang, Ding;  Lewis, Frank L.
Adobe PDF(3217Kb)  |  Favorite  |  View/Download:148/51  |  Submit date:2016/11/09
Adaptive Control  Adaptive Dynamic Programming (Adp)  Data-based  Off-policy Learning  Optimal Control  Policy Gradient  
Opposition-based particle swarm optimization with adaptive mutation strategy 期刊论文
SOFT COMPUTING, 2017, 卷号: 21, 期号: 17, 页码: 5081-5090
Authors:  Dong, Wenyong;  Kang, Lanlan;  Zhang, Wensheng
Favorite  |  View/Download:56/0  |  Submit date:2018/03/03
Particle Swarm Optimization  Adaptive Mutation  Generalized Opposition-based Learning  Adaptive Nonlinear Inertia Weight  
Learning completed discriminative local features for texture classification 期刊论文
PATTERN RECOGNITION, 2017, 卷号: 67, 页码: 263-275
Authors:  Zhang, Zhong;  Liu, Shuang;  Mei, Xing;  Xiao, Baihua;  Zheng, Liang
Favorite  |  View/Download:64/0  |  Submit date:2017/07/18
Texture Classification  Discriminative Learning  Local Binary Patterns  Adaptive Histogram Accumulation  
Neural-network-based synchronous iteration learning method for multi-player zero-sum games 期刊论文
NEUROCOMPUTING, 2017, 卷号: 242, 页码: 73-82
Authors:  Song, Ruizhuo;  Wei, Qinglai;  Song, Biao
Favorite  |  View/Download:166/0  |  Submit date:2017/09/12
Adaptive Dynamic Programming  Approximate Dynamic Programming  Adaptive Critic Designs  Multi-player  Iteration Learning  Neural Network  
Discrete-Time Deterministic Q-Learning: A Novel Convergence Analysis 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 卷号: 47, 期号: 5, 页码: 1224-1237
Authors:  Wei, Qinglai;  Lewis, Frank L.;  Sun, Qiuye;  Yan, Pengfei;  Song, Ruizhuo
Favorite  |  View/Download:53/0  |  Submit date:2017/02/23
Adaptive Critic Designs  Adaptive Dynamic Programming (Adp)  Approximate Dynamic Programming  Neural Networks (Nns)  Neuro-dynamic Programming  Optimal Control  Q-learning  
Online identifier-actor-critic algorithm for optimal control of nonlinear systems 期刊论文
OPTIMAL CONTROL APPLICATIONS & METHODS, 2017, 卷号: 38, 期号: 3, 页码: 317-335
Authors:  Lin, Hanquan;  Wei, Qinglai;  Liu, Derong
Adobe PDF(2888Kb)  |  Favorite  |  View/Download:50/13  |  Submit date:2017/07/18
Adaptive Dynamic Programming  Optimal Control  Discrete-time  Nonlinear System  Neural Network  Online Learning  Lyapunov Method