CASIA OpenIR

Browse/Search Results:  1-10 of 10 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
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:5/0  |  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:35/0  |  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:19/0  |  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:50/1  |  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:99/6  |  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  
Guided Policy Search for Sequential Multitask Learning 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2019, 卷号: 49, 期号: 1, 页码: 216-226
Authors:  Xiong, Fangzhou;  Sun, Biao;  Yang, Xu;  Qiao, Hong;  Huang, Kaizhu;  Hussain, Amir;  Liu, Zhiyong
View  |  Adobe PDF(1059Kb)  |  Favorite  |  View/Download:90/6  |  Submit date:2019/07/12
Elastic weight consolidation (EWC)  guided policy search (GPS)  reinforcement learning (RL)  sequential multitask learning  
Primitives Generation Policy Learning without Catastrophic Forgetting for Robotic Manipulation 会议论文
, China National Convention Center (CNCC), Beijing, November 8-11, 2019
Authors:  Xiong,, Fangzhou;  Liu, Zhiyong;  Huang, Kaizhu;  Yang, Xu;  Amir Hussain
View  |  Adobe PDF(277Kb)  |  Favorite  |  View/Download:52/9  |  Submit date:2020/04/26
Overcoming Catastrophic Forgetting with Self-adaptive Identifiers 会议论文
, Siem Reap, Cambodia, December 13-16, 2018
Authors:  Xiong, Fangzhou;  Liu, Zhiyong;  Yang, Xu
View  |  Adobe PDF(197Kb)  |  Favorite  |  View/Download:28/3  |  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:140/27  |  Submit date:2018/01/02
A Linear Online Guided Policy Search Algorithm 会议论文
, Guangzhou, China, 2017
Authors:  Biao Sun;  Fang-Zhou Xiong;  Zhi-Yong Liu;  Yang X(杨旭)
Adobe PDF(417Kb)  |  Favorite  |  View/Download:158/36  |  Submit date:2018/01/02