Chinese | English

Search in the results

CASIA OpenIR

Browse/Search Results:  1-10 of 51 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
Data-efficient model-based reinforcement learning with trajectory discrimination 期刊论文
COMPLEX & INTELLIGENT SYSTEMS, 2023, 页码: 10
Authors:  Qu, Tuo;  Duan, Fuqing;  Zhang, Junge;  Zhao, Bo;  Huang, Wenzhen
Favorite  |  View/Download：6/0  |  Submit date：2023/11/16
Reinforcement learning  Deep learning  Continuous control task  World model  
Exploration via Joint Policy Diversity for Sparse-Reward Multi-Agent Tasks 会议论文
, Macao, China, 2023-8
Authors:  Pei Xu;  Junge Zhang;  Kaiqi Huang
Adobe PDF(1369Kb)  |  Favorite  |  View/Download：90/15  |  Submit date：2023/06/19
Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks 会议论文
, Washington DC, USA, 2023-2-7
Authors:  Pei Xu;  Junge Zhang;  Qiyue Yin;  Chao Yu;  Yaodong Yang;  Kaiqi Huang
Adobe PDF(2037Kb)  |  Favorite  |  View/Download：65/15  |  Submit date：2023/06/19
deep reinforcement learning  sparse reward  exploration  multi-agent  
Squeezing More Past Knowledge for Online Class-Incremental Continual Learning 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 3, 页码: 722-736
Authors:  Da Yu;  Mingyi Zhang;  Mantian Li;  Fusheng Zha;  Junge Zhang;  Lining Sun;  Kaiqi Huang
Adobe PDF(7599Kb)  |  Favorite  |  View/Download：107/36  |  Submit date：2023/03/02
Catastrophic forgetting  class-incremental learning  continual learning (CL)  experience replay  
Deep Reinforcement Learning With Part-Aware Exploration Bonus in Video Games 期刊论文
IEEE TRANSACTIONS ON GAMES, 2022, 卷号: 14, 期号: 4, 页码: 644-653
Authors:  Xu, Pei;  Yin, Qiyue;  Zhang, Junge;  Huang, Kaiqi
Adobe PDF(1480Kb)  |  Favorite  |  View/Download：108/14  |  Submit date：2023/02/22
Deep learning  exploration  reinforcement learning  video game  
Offline reinforcement learning with representations for actions 期刊论文
INFORMATION SCIENCES, 2022, 卷号: 610, 页码: 746-758
Authors:  Lou, Xingzhou;  Yin, Qiyue;  Zhang, Junge;  Yu, Chao;  He, Zhaofeng;  Cheng, Nengjie;  Huang, Kaiqi
Favorite  |  View/Download：87/0  |  Submit date：2022/11/14
Offline reinforcement learning  Action embedding  
Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning 会议论文
, 意大利, 2022-07
Authors:  Yang GK(杨光开);  Chenhao(陈皓);  Junge Zhang(张俊格);  Qiyue Yin(尹奇跃);  Kaiqi Huang(黄凯奇)
Adobe PDF(2924Kb)  |  Favorite  |  View/Download：145/20  |  Submit date：2022/07/12
Universal adversarial perturbations against object detection 期刊论文
PATTERN RECOGNITION, 2021, 卷号: 110, 期号: 无, 页码: 107584
Authors:  Li, Debang;  Zhang, Junge;  Huang, Kaiqi
Adobe PDF(4553Kb)  |  Favorite  |  View/Download：215/18  |  Submit date：2021/01/06
Adversarial examples  Object detection  Universal adversarial perturbation  
Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning 会议论文
, online, 2021-2
Authors:  Huang, Wenzhen;  Yin Qiyue;  Zhang Junge;  Huang, Kaiqi
Adobe PDF(5676Kb)  |  Favorite  |  View/Download：112/14  |  Submit date：2022/01/11
Composing Good Shots by Exploiting Mutual Relations 会议论文
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Virtual, 14-19, June, 2020
Authors:  Li, Debang;  Zhang, Junge;  Huang, Kaiqi;  Yang, Ming-Hsuan
Adobe PDF(628Kb)  |  Favorite  |  View/Download：106/16  |  Submit date：2021/05/31