CASIA OpenIR

浏览/检索结果: 共78条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Distributed Deep Reinforcement Learning: A Survey and a Multi-player Multi-agent Learning Toolbox 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 3, 页码: 411-430
作者:  Qiyue Yin;  Tongtong Yu;  Shengqi Shen;  Jun Yang;  Meijing Zhao;  Wancheng Ni;  Kaiqi Huang;  Bin Liang;  Liang Wang
Adobe PDF(2923Kb)  |  收藏  |  浏览/下载:25/10  |  提交时间:2024/05/23
Deep reinforcement learning, distributed machine learning, self-play, population-play, toolbox  
兵棋推演的智能决策技术与挑战 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 5, 页码: 913-928
作者:  尹奇跃;  赵美静;  倪晚成;  张俊格;  黄凯奇
Adobe PDF(4513Kb)  |  收藏  |  浏览/下载:32/13  |  提交时间:2024/05/09
兵棋推演  人机对抗  智能决策技术  博弈学习  
AI in Human-computer Gaming: Techniques, Challenges and Opportunities 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 3, 页码: 299-317
作者:  Qi-Yue Yin;  Jun Yang;  Kai-Qi Huang;  Mei-Jing Zhao;  Wan-Cheng Ni;  Bin Liang;  Yan Huang;  Shu Wu;  Liang Wang
Adobe PDF(2608Kb)  |  收藏  |  浏览/下载:35/6  |  提交时间:2024/04/23
Human-computer gaming, AI, intelligent decision making, deep reinforcement learning, self-play  
Contrastive Correlation Preserving Replay for Online Continual Learning 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 1, 页码: 124-139
作者:  Yu, Da;  Zhang, Mingyi;  Li, Mantian;  Zha, Fusheng;  Zhang, Junge;  Sun, Lining;  Huang, Kaiqi
收藏  |  浏览/下载:43/0  |  提交时间:2024/03/26
Task analysis  Correlation  Knowledge transfer  Training  Memory management  Data models  Mutual information  Continual learning  catastrophic forgetting  class-incremental learning  experience replay  
SOTVerse: A User-Defined Task Space of Single Object Tracking 期刊论文
International Journal of Computer Vision, 2023, 页码: 1-59
作者:  Shiyu, Hu;  Xin, Zhao;  Kaiqi Huang
Adobe PDF(53048Kb)  |  收藏  |  浏览/下载:66/6  |  提交时间:2024/01/22
Single object tracking  Experimental environment  Evaluation system  Performance analysis  
单目标跟踪中的视觉智能评估技术综述 期刊论文
中国图象图形学报, 2023, 页码: 1-30
作者:  胡世宇;  赵鑫;  黄凯奇
Adobe PDF(10669Kb)  |  收藏  |  浏览/下载:135/37  |  提交时间:2024/01/22
智能评估技术  竞赛和数据集  视觉跟踪能力  单目标跟踪  目标跟踪算法  
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
作者:  Da Yu;  Mingyi Zhang;  Mantian Li;  Fusheng Zha;  Junge Zhang;  Lining Sun;  Kaiqi Huang
Adobe PDF(7599Kb)  |  收藏  |  浏览/下载:260/98  |  提交时间:2023/03/02
Catastrophic forgetting  class-incremental learning  continual learning (CL)  experience replay  
Global Instance Tracking: Locating Target More Like Humans 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 1, 页码: 576-592
作者:  Hu, Shiyu;  Zhao, Xin;  Huang, Lianghua;  Huang, Kaiqi
Adobe PDF(15055Kb)  |  收藏  |  浏览/下载:240/55  |  提交时间:2023/02/22
Global instance tracking  single object tracking  benchmark dataset  performance evaluation  human tracking ability  
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
作者:  Xu, Pei;  Yin, Qiyue;  Zhang, Junge;  Huang, Kaiqi
Adobe PDF(1480Kb)  |  收藏  |  浏览/下载:318/78  |  提交时间: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
作者:  Lou, Xingzhou;  Yin, Qiyue;  Zhang, Junge;  Yu, Chao;  He, Zhaofeng;  Cheng, Nengjie;  Huang, Kaiqi
收藏  |  浏览/下载:181/0  |  提交时间:2022/11/14
Offline reinforcement learning  Action embedding