中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共7条，第1-7条 帮助

限定条件                        
已选(0)清除 条数/页：   排序方式：
Centralized Cooperative Exploration Policy for Continuous Control Tasks 会议论文
Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, London, United Kingdom, May 29–June 2, 2023
作者:  Chao Li;  Chen Gong;  Qiang He;  Xinwen Hou;  Yu Liu
Adobe PDF(2175Kb)  |  收藏  |  浏览/下载：49/19  |  提交时间：2024/05/30
continuous control tasks  cooperative exploration  
Stable Training of Bellman Error in Reinforcement Learning 会议论文
, Thailand, November 18–22
作者:  Gong C(龚晨);  Bai YP(白云鹏);  Hou XW(侯新文);  Ji XH(季晓慧)
Adobe PDF(2416Kb)  |  收藏  |  浏览/下载：130/37  |  提交时间：2023/06/27
Learning Hierarchical Graph Convolutional Neural Network for Object Navigation 会议论文
, 西英格兰大学计算机科学与创新技术系, 2022年9月6日-2022年9月9日
作者:  Tao Xu;  Xu Yang;  Suiwu Zheng
Adobe PDF(1220Kb)  |  收藏  |  浏览/下载：179/58  |  提交时间：2023/05/31
Reinforcement Learning Based Variable Impedance Control for High Precision Human-robot Collaboration Tasks 会议论文
, 线上, July 3-5, 2021
作者:  Meng, Yan;  Su, Jianhua;  Wu, Jiaxi
Adobe PDF(6621Kb)  |  收藏  |  浏览/下载：220/52  |  提交时间：2022/06/15
Learning Smooth and Omnidirectional Locomotion for Quadruped Robots 会议论文
, Chongqing, China, 2021-7
作者:  Wu, Jiaxi;  Wang, Chen'an;  Zhang, Dianmin;  Zhong, Shanlin;  Wang, Boxing;  Qiao, Hong
Adobe PDF(1436Kb)  |  收藏  |  浏览/下载：218/58  |  提交时间：2022/06/14
Quadruped Robot  Reinforcement Learning  
Trajectory-based Split Hindsight Reverse Curriculum Learning 会议论文
, Prague, Czech Republic, 2021-9
作者:  Wu, Jiaxi;  Zhang, Dianmin;  Zhong, Shanlin;  Qiao, Hong
Adobe PDF(5094Kb)  |  收藏  |  浏览/下载：242/60  |  提交时间：2022/06/14
Reinforcement Learning  Curriculum Learning  
Improving Learning Efficiency of Recurrent Neural Network through Adjusting Weights of All Layers in a Biologically-inspired Framework 会议论文
, Anchorage, AK, USA, 2017-5-14
作者:  Huang, Xiao;  Wu, Wei;  Yin, Peijie;  Qiao, Hong
浏览  |  Adobe PDF(466Kb)  |  收藏  |  浏览/下载：259/66  |  提交时间：2020/06/09
Brain-inspired model  emotion  motion learning  recurrent neural network