中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共4条，第1-4条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Supervised assisted deep reinforcement learning for emergency voltage control of power systems 期刊论文
NEUROCOMPUTING, 2022, 卷号: 475, 页码: 69-79
作者:  Li, Xiaoshuang;  Wang, Xiao;  Zheng, Xinhu;  Dai, Yuxin;  Yu, Zhihong;  Zhang, Jun Jason;  Bu, Guangquan;  Wang, Fei-Yue
Adobe PDF(2551Kb)  |  收藏  |  浏览/下载：290/60  |  提交时间：2022/06/06
Deep reinforcement learning  Behavioral cloning  Dynamic demonstration  Emergency control  
SADRL: Merging human experience with machine intelligence via supervised assisted deep reinforcement learning 期刊论文
NEUROCOMPUTING, 2022, 卷号: 467, 页码: 300-309
作者:  Li, Xiaoshuang;  Wang, Xiao;  Zheng, Xinhu;  Jin, Junchen;  Huang, Yanhao;  Zhang, Jun Jason;  Wang, Fei-Yue
Adobe PDF(1244Kb)  |  收藏  |  浏览/下载：276/60  |  提交时间：2021/12/28
Deep reinforcement learning  Behavioral cloning  Dynamic demonstration  Double DQN  
Estimation of human impedance and motion intention for constrained human-robot interaction 期刊论文
NEUROCOMPUTING, 2020, 卷号: 390, 页码: 268-279
作者:  Yu, Xinbo;  Li, Yanan;  Zhang, Shuang;  Xue, Chengqian;  Wang, Yu
收藏  |  浏览/下载：172/0  |  提交时间：2020/06/22
Human motion intention estimation  Impedance learning  Adaptive neural network control  Full-state constraints  Barrier Lyapunov functions  
Adaptive neural control of quadruped robots with input deadzone 期刊论文
NEUROCOMPUTING, 2019, 卷号: 329, 页码: 486-494
作者:  Zhang, Shuang;  Zhang, Donghao;  Chang, Cheng;  Fu, Qiang;  Wang, Yu
收藏  |  浏览/下载：246/0  |  提交时间：2019/07/12
Quadruped robot  Neural networks  Input deadzone  Full state feedback  Output feedback