CASIA OpenIR

Browse/Search Results:  1-6 of 6 Help

Filters    
Selected(0)Clear Items/Page:    Sort:
Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 10, 页码: 5105-5120
Authors:  Li, Debang;  Wu, Huikai;  Zhang, Junge;  Huang, Kaiqi
Favorite  |  View/Download:14/0  |  Submit date:2019/12/16
Reinforcement learning  adversarial learning  image cropping  
Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 卷号: 28, 期号: 10, 页码: 5105-5120
Authors:  Li, Debang;  Wu, Huikai;  Zhang, Junge;  Huang, Kaiqi
Favorite  |  View/Download:16/0  |  Submit date:2019/12/16
Reinforcement learning  adversarial learning  image cropping  
Optimized Adaptive Nonlinear Tracking Control Using Actor-Critic Reinforcement Learning Strategy 期刊论文
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 卷号: 15, 期号: 9, 页码: 4969-4977
Authors:  Wen, Guoxing;  Chen, C. L. Philip;  Ge, Shuzhi Sam;  Yang, Hongli;  Liu, Xiaoguang
Favorite  |  View/Download:7/0  |  Submit date:2019/12/16
Lyapunov function  neural networks (NNs)  nonlinear systems  optimized tracking control  reinforcement learning (RL) of actor-critic architecture  
Adaptive Tracking Control of Surface Vessel Using Optimized Backstepping Technique 期刊论文
IEEE TRANSACTIONS ON CYBERNETICS, 2019, 卷号: 49, 期号: 9, 页码: 3420-3431
Authors:  Wen, Guoxing;  Ge, Shuzhi Sam;  Chen, C. L. Philip;  Tu, Fangwen;  Wang, Shengnan
Favorite  |  View/Download:6/0  |  Submit date:2019/12/16
Actor-critic architecture  Lyapunov stability  optimized backstepping (OB)  reinforcement learning (RL)  surface vessel  
Optimized Multi-Agent Formation Control Based on an Identifier-Actor--Critic Reinforcement Learning Algorithm 期刊论文
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2018, 卷号: 26, 期号: 5, 页码: 2719-2731
Authors:  Wen, Guoxing;  Chen, C. L. Philip;  Feng, Jun;  Zhou, Ning
Favorite  |  View/Download:11/0  |  Submit date:2019/12/16
Fuzzy logic systems (FLSs)  identifier-actor-critic architecture  multi-agent formation  optimized formation control  reinforcement learning (RL)  
Policy Iteration Algorithm Based Fault Tolerant Tracking Control: An Implementation on Reconfigurable Manipulators 期刊论文
JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2018, 卷号: 13, 期号: 4, 页码: 1739-1750
Authors:  Li, Yuanchun;  Xia, Hongbing;  Zhao, Bo
View  |  Adobe PDF(708Kb)  |  Favorite  |  View/Download:99/7  |  Submit date:2018/10/10
Adaptive dynamic programming  Policy iteration  Fault tolerant tracking control  Reconfigurable manipulators  Neural network