CASIA OpenIR

浏览/检索结果: 共23条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Measuring and Predicting Visual Importance of Similar Objects 期刊论文
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2016, 卷号: 22, 期号: 12, 页码: 2564-2578
作者:  Kong, Yan;  Dong, Weiming;  Mei, Xing;  Ma, Chongyang;  Lee, Tong-Yee;  Lyu, Siwei;  Huang, Feiyue;  Zhang, Xiaopeng
浏览  |  Adobe PDF(2594Kb)  |  收藏  |  浏览/下载:459/123  |  提交时间:2016/04/13
Similar Objects  Visual Importance  Listwise Ranking  
Event-based input-constrained nonlinear H infinity state feedback with adaptive critic and neural implementation 期刊论文
NEUROCOMPUTING, 2016, 卷号: 214, 期号: *, 页码: 848-856
作者:  Wang, Ding;  Mu, Chaoxu;  Zhang, Qichao;  Liu, Derong
浏览  |  Adobe PDF(1090Kb)  |  收藏  |  浏览/下载:342/135  |  提交时间:2017/02/14
Adaptive Critic Learning (Acl)  Adaptive Dynamic Programming (Adp)  Event-based Control  Hamilton-jacobi-isaacs (Hji) Equation  Input Constraints  Neural Networks  Nonlinear H-infinity Control  State Feedback  
Decentralized guaranteed cost control of interconnected systems with uncertainties: A learning-based optimal control strategy 期刊论文
NEUROCOMPUTING, 2016, 卷号: 214, 页码: 297-306
作者:  Wang, Ding;  Liu, Derong;  Mu, Chaoxu;  Ma, Hongwen
Adobe PDF(1113Kb)  |  收藏  |  浏览/下载:363/119  |  提交时间:2017/02/14
Adaptive Dynamic Programming  Decentralized Control  Guaranteed Cost Control  Interconnected Systems  Learning Control  Neural Networks  Optimal Control  Uncertain Plant  
Developing a cooperative bidding framework for sponsored search markets - An evolutionary perspective 期刊论文
INFORMATION SCIENCES, 2016, 卷号: 369, 期号: NA, 页码: 674-689
作者:  Yuan, Yong;  Wang, Fei-Yue;  Zeng, Daniel
浏览  |  Adobe PDF(2247Kb)  |  收藏  |  浏览/下载:389/132  |  提交时间:2016/12/26
Sponsored Search  Bid Inflation  Evolutionary Game Theory  Coevolutionary Simulation  
Data-based robust adaptive control for a class of unknown nonlinear constrained-input systems via integral reinforcement learning 期刊论文
INFORMATION SCIENCES, 2016, 卷号: 369, 页码: 731-747
作者:  Yang, Xiong;  Liu, Derong;  Luo, Biao;  Li, Chao
收藏  |  浏览/下载:213/0  |  提交时间:2016/12/26
Adaptive Dynamic Programming  Input Constraint  Neural Networks  Optimal Control  Reinforcement Learning  Robust Control  
Data-Based Adaptive Critic Designs for Nonlinear Robust Optimal Control With Uncertain Dynamics 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2016, 卷号: 46, 期号: 11, 页码: 1544-1555
作者:  Wang, Ding;  Liu, Derong;  Zhang, Qichao;  Zhao, Dongbin
浏览  |  Adobe PDF(1082Kb)  |  收藏  |  浏览/下载:427/193  |  提交时间:2017/02/14
Adaptive Critic Designs  Adaptive Dynamic Programming  Intelligent Control  Neural Networks  Policy Iteration  Robust Optimal Control  System Identification  Uncertain Nonlinear Systems  
Model-free reinforcement learning for nonlinear zero-sum games with simultaneous explorations 会议论文
, Vancouver, Canada, 2016-7
作者:  Zhang, Qichao;  Zhao, Dongbin;  Zhu, Yuanheng;  Chen, Xi
Adobe PDF(339Kb)  |  收藏  |  浏览/下载:263/86  |  提交时间:2017/05/04
Model-Free Optimal Tracking Control via Critic-Only Q-Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 卷号: 27, 期号: 10, 页码: 2134-2144
作者:  Luo, Biao;  Liu, Derong;  Huang, Tingwen;  Wang, Ding;  Luo,Biao
浏览  |  Adobe PDF(1521Kb)  |  收藏  |  浏览/下载:565/283  |  提交时间:2016/10/24
Critic-only Q-learning (Coql)  Model-free  Nonaffine Nonlinear Systems  Optimal Tracking Control  
面向数据高效利用的深度强化学习方法及应用 学位论文
, 北京: 中国科学院研究生院, 2016
作者:  王海涛
Adobe PDF(2611Kb)  |  收藏  |  浏览/下载:397/14  |  提交时间:2016/06/15
人工智能  强化学习  深度学习  经验回放  深度强化学习  数据采样  
基于数据的系统分析和自适应优化控制器设计 学位论文
, 北京: 中国科学院大学, 2016
作者:  阎鹏飞
Adobe PDF(2184Kb)  |  收藏  |  浏览/下载:290/4  |  提交时间:2016/06/21
基于数据的控制  自适应控制  自适应动态规划  增强学习  误差分析