中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共5条，第1-5条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Adaptive bias-variance trade-off in advantage estimator for actor-critic algorithms 期刊论文
NEURAL NETWORKS, 2024, 卷号: 169, 页码: 764-777
作者:  Chen, Yurou;  Zhang, Fengyi;  Liu, Zhiyong
收藏  |  浏览/下载：16/0  |  提交时间：2024/02/22
Reinforcement Learning  Policy gradient  Actor-critic  Value function  Bias-variance trade-off  
Policy generation network for zero-shot policy learning 期刊论文
COMPUTATIONAL INTELLIGENCE, 2023, 页码: 27
作者:  Qian, Yiming;  Zhang, Fengyi;  Liu, Zhiyong
收藏  |  浏览/下载：47/0  |  提交时间：2023/11/17
knowledge representation  lifelong reinforcement learning  zero-shot policy generation  
Markovian Policy Network for Efficient Robot Learning 期刊
创刊日期: 2022,
主办者:  Zhang FY(张丰一), Yurou Chen, Zhiyong Liu
Adobe PDF(2453Kb)  |  收藏  |  浏览/下载：199/70  |  提交时间：2023/01/12
Efficient robot learning  Structural prior knowledge  Reinforcement learning  Graph neural network  
Learning Individual Features to Decompose State Space for Robotic Skill Learning 会议论文
, Online, 2020-8
作者:  Fengyi Zhang;  Fangzhou Xiong;  Zhiyong Liu
Adobe PDF(622Kb)  |  收藏  |  浏览/下载：133/49  |  提交时间：2023/01/12
Robotic Skill Learning  Graph Neural Networks  State Decomposition  
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
作者:  Zhang, Fengyi;  Liu, Zhiyong;  Xiong, Fangzhou;  Su, Jianhua;  Qiao, Hong
Adobe PDF(1550Kb)  |  收藏  |  浏览/下载：316/43  |  提交时间：2020/07/20
Skill transfer learning  Serial structures  Robot skill learning  Graph Neural Network