CASIA OpenIR
(Note: the search results are based on claimed items)

Browse/Search Results:  1-10 of 26 Help

Filters        
Selected(0)Clear Items/Page:    Sort:
Reinforcement learning for robust adaptive control of partially unknown nonlinear systems subject to unmatched uncertainties 期刊论文
INFORMATION SCIENCES, 2018, 卷号: 463, 页码: 307-322
Authors:  Yang, Xiong;  He, Haibo;  Wei, Qinglai;  Luo, Biao
Favorite  |  View/Download:44/0  |  Submit date:2018/10/10
Adaptive Dynamic Programming  Neural Networks  Optimal Control  Reinforcement Learning  Robust Control  Unmatched Uncertainty  
An adaptive critic approach to event-triggered robust control of nonlinear systems with unmatched uncertainties 期刊论文
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2018, 卷号: 28, 期号: 10, 页码: 3501-3519
Authors:  Yang, Xiong;  He, Haibo;  Wei, Qinglai
Favorite  |  View/Download:38/0  |  Submit date:2018/10/10
Adaptive Critic Approach  Event-triggered Control  Reinforcement Learning  Robust Control  Unmatched Uncertainty  
Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 期号: 4, 页码: 1226-1238
Authors:  Wei, Qinglai;  Li, Benkai;  Song, Ruizhuo
View  |  Adobe PDF(2475Kb)  |  Favorite  |  View/Download:71/15  |  Submit date:2017/02/23
Adaptive Critic Designs  Adaptive Dynamic Programming (Adp)  Approximate Dynamic Programming  Generalized Policy Iteration (Gpi)  Neural Networks  Neurodynamic Programming  Nonlinear Systems  Optimal Control  Reinforcement Learning  
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:51/0  |  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
View  |  Adobe PDF(2888Kb)  |  Favorite  |  View/Download:49/13  |  Submit date:2017/07/18
Adaptive Dynamic Programming  Optimal Control  Discrete-time  Nonlinear System  Neural Network  Online Learning  Lyapunov Method  
Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 卷号: 28, 期号: 3, 页码: 704-713
Authors:  Song, Ruizhuo;  Lewis, Frank L.;  Wei, Qinglai
Favorite  |  View/Download:35/0  |  Submit date:2017/05/05
Adaptive Critic Designs  Adaptive Dynamic Programming (Adp)  Approximate Dynamic Programming  Integral Reinforcement Learning (Irl)  Nonlinear Systems  Nonzero Sum (Nzs)  Off-policy  
PDP: parallel dynamic programming 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2017, 卷号: 4, 期号: 1, 页码: 1-5
Authors:  Fei-Yue Wang;  Jie Zhang;  Qinglai Wei;  Xinhu Zheng;  Li Li
View  |  Adobe PDF(3789Kb)  |  Favorite  |  View/Download:63/0  |  Submit date:2018/01/04
Parallel Dynamic Programming  Dynamic Programming  Adaptive Dynamic Programming  Reinforcementlearning  Deep Learning  Neural Networks  Artificial Intelligence.  
Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 3, 页码: 840-853
Authors:  Wei, Qinglai;  Liu, Derong;  Lin, Hanquan;  Derong Liu
View  |  Adobe PDF(2015Kb)  |  Favorite  |  View/Download:105/36  |  Submit date:2016/06/14
Adaptive Critic Designs  Adaptive Dynamic Programming (Adp)  Approximate Dynamic Programming  Neural Networks  Neuro-dynamic Programming  Optimal Control  Reinforcement Learning  Value Iteration  
Neuro-optimal tracking control for a class of discrete-time nonlinear systems via generalized value iteration adaptive dynamic programming approach 期刊论文
SOFT COMPUTING, 2016, 卷号: 20, 期号: 2, 页码: 697-706
Authors:  Wei, Qinglai;  Liu, Derong;  Xu, Yancai;  Qinglai Wei
View  |  Adobe PDF(790Kb)  |  Favorite  |  View/Download:160/74  |  Submit date:2016/06/14
Adaptive Dynamic Programming  Approximate Dynamic Programming  Adaptive Critic Designs  Optimal Control  Neural Networks  Nonlinear Systems  Reinforcement Learning