CASIA OpenIR

Browse/Search Results:  1-5 of 5 Help

Filters    
Selected(0)Clear Items/Page:    Sort:
Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks 期刊论文
NEURAL NETWORKS, 2018, 期号: 1, 页码: 1-27
Authors:  Shi, Jing;  Xu, Jiaming;  Yao, Yiqun;  Xu, Bo
View  |  Adobe PDF(533Kb)  |  Favorite  |  View/Download:101/18  |  Submit date:2018/10/30
One-shot Learning  Memory  Attention  Deep Reinforcement  
Learning to Activate Logic Rules for Textual Reasoning 期刊论文
NEURAL NETWORKS, 2018, 期号: 106, 页码: 42-49
Authors:  Yao, Yiqun;  Xu, Jiaming;  Shi, Jing;  Xu, Bo
View  |  Adobe PDF(449Kb)  |  Favorite  |  View/Download:156/65  |  Submit date:2018/10/09
Natural Language Reasoning  Memory Networks  Image Schema  Logic Rules  Reinforcement Learning  
Reinforcement learning solution for HJB equation arising in constrained optimal control problem 期刊论文
NEURAL NETWORKS, 2015, 卷号: 71, 期号: 0, 页码: 150-158
Authors:  Luo, Biao;  Wu, Huai-Ning;  Huang, Tingwen;  Liu, Derong
View  |  Adobe PDF(530Kb)  |  Favorite  |  View/Download:167/78  |  Submit date:2016/03/30
Constrained Optimal Control  Data-based  Off-policy Reinforcement Learning  Hamilton-jacobi-bellman Equation  The Method Of Weighted Residuals  
Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning 期刊论文
NEURAL NETWORKS, 2014, 卷号: 55, 页码: 30-41
Authors:  Yang, Xiong;  Liu, Derong;  Wang, Ding;  Wei, Qinglai
View  |  Adobe PDF(684Kb)  |  Favorite  |  View/Download:147/59  |  Submit date:2015/08/12
Adaptive Critic Design  Neural Network  Nonaffine Nonlinear System  Online Learning  Reinforcement Learning  
An iterative is an element of-optimal control scheme for a class of discrete-time nonlinear systems with unfixed initial state 期刊论文
NEURAL NETWORKS, 2012, 卷号: 32, 期号: x, 页码: 236-244
Authors:  Wei, Qinglai;  Liu, Derong;  Derong Liu
View  |  Adobe PDF(438Kb)  |  Favorite  |  View/Download:59/10  |  Submit date:2015/08/12
Adaptive Dynamic Programming  Approximate Dynamic Programming  Is An Element Of-optimal Control  Finite Horizon  Neural Networks