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

Browse/Search Results:  1-7 of 7 Help

Filters            
Selected(0)Clear Items/Page:    Sort:
Convolutional fitted Q iteration for vision-based control problems 会议论文
, Vancouver, BC, Canada, 24-29 July 2016
Authors:  Zhao Dongbin;  Zhu Yuanheng;  Lv Le;  Chen Yaran;  Zhang Qichao
View  |  Adobe PDF(240Kb)  |  Favorite  |  View/Download:121/32  |  Submit date:2017/05/08
Model-free reinforcement learning for nonlinear zero-sum games with simultaneous explorations 会议论文
, Vancouver, Canada, 2016-7
Authors:  Zhang, Qichao;  Zhao, Dongbin;  Zhu, Yuanheng;  Chen, Xi
View  |  Adobe PDF(339Kb)  |  Favorite  |  View/Download:83/29  |  Submit date:2017/05/04
Deep reinforcement learning with Experience Replay based on SARSA 会议论文
, *, 2016-9
Authors:  Zhao,Dongbin(赵冬斌);  Wang,Haitao;  Shao,Kun;  Zhu,Yuanheng
View  |  Adobe PDF(1288Kb)  |  Favorite  |  View/Download:105/57  |  Submit date:2018/01/04
Deep Learning  Reinforcement Learning  Experience Replay  q Learning  Sarsa Learning  
Using reinforcement learning techniques to solve continuous-time non-linear optimal tracking problem without system dynamics 期刊论文
IET CONTROL THEORY AND APPLICATIONS, 2016, 卷号: 10, 期号: 12, 页码: 1339-1347
Authors:  Zhu, Yuanheng;  Zhao, Dongbin;  Li, Xiangjun
View  |  Adobe PDF(976Kb)  |  Favorite  |  View/Download:128/55  |  Submit date:2016/12/26
Nonlinear Control Systems  Continuous Time Systems  Learning (Artificial Intelligence)  Optimal Control  Dynamic Programming  Lyapunov Methods  Linear Systems  Reinforcement Learning  Continuous-time Problem  Nonlinear Optimal Tracking Problem  Adaptive Dynamic Programming  Model-free Adaptive Optimal Tracking Algorithm  Lyapunov Analysis  Linear System  
Experience Replay for Optimal Control of Nonzero-Sum Game Systems With Unknown Dynamics 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2016, 卷号: 46, 期号: 3, 页码: 854-865
Authors:  Zhao, Dongbin;  Zhang, Qichao;  Wang, Ding;  Zhu, Yuanheng
View  |  Adobe PDF(1769Kb)  |  Favorite  |  View/Download:154/78  |  Submit date:2016/06/14
Adaptive Dynamic Programming (Adp)  Experience Replay  Nonzero-sum (Nzs) Games  Optimal Control  Unknown Dynamics  
深度强化学习综述:兼论计算机围棋的发展 期刊论文
控制理论与应用, 2016, 卷号: 33, 期号: 6, 页码: 701-717
Authors:  赵冬斌;  邵坤;  朱圆恒;  李栋;  陈亚冉;  王海涛;  刘德荣;  周彤;  王成红
View  |  Adobe PDF(2816Kb)  |  Favorite  |  View/Download:563/231  |  Submit date:2017/09/13
深度强化学习  初弈号  深度学习  强化学习  人工智能  
概率近似正确的强化学习算法解决连续状态空间控制问题 期刊论文
控制理论与应用, 2016, 卷号: 33, 期号: 12, 页码: 1603-1613
Authors:  朱圆恒;  赵冬斌
View  |  Adobe PDF(1544Kb)  |  Favorite  |  View/Download:37/9  |  Submit date:2017/09/13
强化学习  概率近似正确  Kd树  双连杆机械臂