Chinese | English

Search in the results

CASIA OpenIR

Browse/Search Results:  1-10 of 11 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Zero-shot policy generation in lifelong reinforcement learning q 期刊论文
NEUROCOMPUTING, 2021, 卷号: 446, 页码: 65-73
Authors:  Qian, Yi-Ming;  Xiong, Fang-Zhou;  Liu, Zhi-Yong
Favorite  |  View/Download：10/0  |  Submit date：2021/08/15
Lifelong reinforcement learning  Generalization policy  Task domain  
State Primitive Learning to Overcome Catastrophic Forgetting in Robotics 期刊论文
COGNITIVE COMPUTATION, 2020, 页码: 9
Authors:  Xiong, Fangzhou;  Liu, Zhiyong;  Huang, Kaizhu;  Yang, Xu;  Qiao, Hong
Favorite  |  View/Download：21/0  |  Submit date：2021/01/06
Catastrophic forgetting  State primitives  Robotics  Continual learning  
WAGNN: A Weighted Aggregation Graph Neural Network for robot skill learning 期刊论文
ROBOTICS AND AUTONOMOUS SYSTEMS, 2020, 卷号: 130, 页码: 9
Authors:  Zhang, Fengyi;  Liu, Zhiyong;  Xiong, Fangzhou;  Su, Jianhua;  Qiao, Hong
Favorite  |  View/Download：62/0  |  Submit date：2020/07/20
Skill transfer learning  Serial structures  Robot skill learning  Graph Neural Network  
WAGNN: A Weighted Aggregation Graph Neural Network for robot skill learning 期刊论文
ROBOTICS AND AUTONOMOUS SYSTEMS, 2020, 卷号: 130, 页码: 9
Authors:  Zhang, Fengyi;  Liu, Zhiyong;  Xiong, Fangzhou;  Su, Jianhua;  Qiao, Hong
Favorite  |  View/Download：43/0  |  Submit date：2020/07/20
Skill transfer learning  Serial structures  Robot skill learning  Graph Neural Network  
Encoding Primitives Generation Policy Learning for Robotic Arm to Overcome Catastrophic Forgetting in Sequential Multi-tasks Learning 期刊论文
Neural Networks, 2020, 期号: 2020.06.003, 页码: 12
Authors:  Xiong, Fangzhou;  Liu, Zhiyong;  Huang, Kaizhu;  Yang, Xu;  Qiao, Hong;  Amir Hussain
View  |  Adobe PDF(646Kb)  |  Favorite  |  View/Download：67/2  |  Submit date：2020/06/09
Sequential multi-tasks learning, Continual learning, Catastrophic forgetting, Robotics  
机器人持续性策略学习算法研究 学位论文
, 中国科学院自动化研究所: 中国科学院大学, 2020
Authors:  熊方舟
Adobe PDF(3642Kb)  |  Favorite  |  View/Download：132/10  |  Submit date：2020/06/09
持续学习  策略学习  机器人  灾难性遗忘  状态基元  
无权访问的条目 会议论文
Authors:  Xiong,, Fangzhou;  Liu, Zhiyong;  Huang, Kaizhu;  Yang, Xu;  Amir Hussain
Adobe PDF(277Kb)  |  Favorite  |  View/Download：53/9  |  Submit date：2020/04/26
无权访问的条目 期刊论文
Authors:  Xiong, Fangzhou;  Sun, Biao;  Yang, Xu;  Qiao, Hong;  Huang, Kaizhu;  Hussain, Amir;  Liu, Zhiyong
Adobe PDF(1059Kb)  |  Favorite  |  View/Download：91/7  |  Submit date：2019/07/12
无权访问的条目 会议论文
Authors:  Xiong, Fangzhou;  Liu, Zhiyong;  Yang, Xu
Adobe PDF(197Kb)  |  Favorite  |  View/Download：29/3  |  Submit date：2020/04/26
A Bayesian Posterior Updating Algorithm in Reinforcement Learning 会议论文
, Guangzhou, China, 2017
Authors:  Fang-Zhou Xiong;  Zhi-Yong Liu;  Xu Yang;  Biao Sun;  Hong Qiao
Adobe PDF(268Kb)  |  Favorite  |  View/Download：154/29  |  Submit date：2018/01/02