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

Browse/Search Results:  1-10 of 16 Help

Filters        
Selected(0)Clear Items/Page:    Sort:
Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2019, 卷号: 49, 期号: 8, 页码: 2874-2885
Authors:  Zhang, Qichao;  Zhao, Dongbin
View  |  Adobe PDF(1021Kb)  |  Favorite  |  View/Download:15/0  |  Submit date:2019/07/12
Integral reinforcement learning (IRL)  neural network (NN)  nonzero-sum (NZS) games  off-policy  single-critic  unknown drift dynamics  
StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning 期刊论文
IEEE Transactions on Emerging Topics in Computational Intelligence, 2019, 卷号: 3, 期号: 1, 页码: 73-84
Authors:  Kun Shao;  Yuanheng Zhu;  Dongbin Zhao
View  |  Adobe PDF(4125Kb)  |  Favorite  |  View/Download:60/41  |  Submit date:2019/04/22
Reinforcement Learning, Transfer Learning, Curriculum Learning, Neural Network, Game Ai  
Deep reinforcement learning based automatic exploration for navigation in unknown environment 期刊论文
IEEE Transactions on Neural Network and Learning Systems, 2019, 期号: early acess, 页码: 1-13
Authors:  Li Haoran;  Zhang Qichao;  Zhao Dongbin
View  |  Adobe PDF(2946Kb)  |  Favorite  |  View/Download:38/28  |  Submit date:2019/10/09
Automatic Exploration  Deep Reinforcement Learning  Optimal Decision  Partial Observation  
Off-Policy Reinforcement Learning for Partially Unknown Nonzero-Sum Games 会议论文
, Guangzhou China, November 14–18
Authors:  Zhang,Qichao;  Zhao,Dongbin;  Zhang,Sibo
View  |  Adobe PDF(119Kb)  |  Favorite  |  View/Download:74/15  |  Submit date:2017/12/28
Event-Triggered H-infinity Control for Continuous-Time Nonlinear System via Concurrent Learning 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2017, 卷号: 47, 期号: 7, 页码: 1071-1081
Authors:  Zhang, Qichao;  Zhao, Dongbin;  Zhu, Yuanheng
View  |  Adobe PDF(2937Kb)  |  Favorite  |  View/Download:198/122  |  Submit date:2017/05/04
Concurrent Learning  Event-triggered Control  H-infinity Optimal Control  Neural Networks (Nns)  Zero-sum (Zs) Game  
Data-driven adaptive dynamic programming for continuous-time fully cooperative games with partially constrained inputs 期刊论文
NEUROCOMPUTING, 2017, 卷号: 238, 期号: *, 页码: 377-386
Authors:  Zhang, Qichao;  Zhao, Dongbin;  Zhu, Yuanheng
View  |  Adobe PDF(1508Kb)  |  Favorite  |  View/Download:163/87  |  Submit date:2017/05/04
Adaptive Dynamic Programming  Optimal Control  Neural Network  Fully Cooperative Games  Data-driven  Constrained Input  
Event-Triggered Optimal Control for Partially Unknown Constrained-Input Systems via Adaptive Dynamic Programming 期刊论文
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 卷号: 64, 期号: 5, 页码: 4101-4109
Authors:  Zhu, Yuanheng;  Zhao, Dongbin;  He, Haibo;  Ji, Junhong
View  |  Adobe PDF(2325Kb)  |  Favorite  |  View/Download:139/70  |  Submit date:2017/09/12
Actor-critic-identifier  Concurrent Learning  Constrained Input  Event-triggered (Et) Control  Hamilton-jacobi-bellman (Hjb) Equation  
Policy Iteration for Hinfinity Optimal Control of Polynomial Nonlinear Systems via Sum of Squares Programming 期刊论文
IEEE Transactions on Cybernetics, 2017, 期号: PP, 页码: 1-9
Authors:  Yuanheng Zhu;  Zhao DB(赵冬斌)
View  |  Adobe PDF(894Kb)  |  Favorite  |  View/Download:69/35  |  Submit date:2017/09/13
Adaptive Dynamic Programming (Adp)  H∞ Optimal Control  Policy Iteration (Pi)  Polynomial Nonlinear Systems  Sum Of Squares (Sos)  
Data-driven adaptive dynamic programming for two-player nonzero-sum game 会议论文
, Chongqing, China, 2017-5
Authors:  Zhang, Qichao;  Zhao, Dongbin
View  |  Adobe PDF(141Kb)  |  Favorite  |  View/Download:126/67  |  Submit date:2017/05/04
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:81/28  |  Submit date:2017/05/04