CASIA OpenIR

Browse/Search Results:  1-10 of 2181 Help

Selected(0)Clear Items/Page:    Sort:
连续控制任务中集成策略的多样性探索研究 学位论文
, 2024
Authors:  李超
Adobe PDF(7255Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2024/05/28
强化学习  集成学习  价值估计  多样性探索  
事件因果关系挖掘关键技术研究 学位论文
, 2024
Authors:  何致涛
Adobe PDF(3575Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2024/05/28
事件因果关系识别  事件因果关系解释生成  预训练语言模型  多智能体  
基于强化学习的机器人操作策略表征与学习 学位论文
, 2024
Authors:  杨依明
Adobe PDF(19731Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2024/05/28
强化学习  机器人操作  机器人控制  策略表征  
D2AH-PPO: Playing ViZDoom With Object-Aware Hierarchical Reinforcement Learning 会议论文
, 中国重庆, 2024.5.7-5.9
Authors:  Niu LY(钮龙宇);  Wan J(万军)
Adobe PDF(1645Kb)  |  Favorite  |  View/Download:9/1  |  Submit date:2024/05/28
深度强化学习  表征学习  分层学习  
基于脑电信号的跨域情绪识别及抑郁评估研究 学位论文
, 2024
Authors:  杨子阳
Adobe PDF(5686Kb)  |  Favorite  |  View/Download:25/0  |  Submit date:2024/05/28
脑电 (EEG)  情绪识别  抑郁评估  深度学习  域适应  
融合专家知识与强化学习的自动驾驶策略研究 学位论文
, 2024
Authors:  王宇霄
Adobe PDF(2599Kb)  |  Favorite  |  View/Download:11/1  |  Submit date:2024/05/28
自动驾驶,深度模仿学习,深度强化学习,图神经网络  
3D-Aware Adversarial Makeup Generation for Facial Privacy Protection 期刊论文
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 页码: 16
Authors:  Yueming Lyu;  Yue Jiang;  Ziwen He;  Bo Peng;  Yunfan Liu;  Jing Dong
Adobe PDF(13973Kb)  |  Favorite  |  View/Download:3/1  |  Submit date:2024/05/28
面向高仿真场景的深度强化学习算法研究 学位论文
, 2024
Authors:  钮龙宇
Adobe PDF(9528Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2024/05/28
深度强化学习  高仿真场景  分层学习  模仿学习  表征学习  
BEVBert: Multimodal Map Pre-training for Language-guided Navigation 会议论文
Proceedings of the IEEE International Conference on Computer Vision, Paris, France, 2023-10-2
Authors:  Dong An;  Yuankai Qi;  Yangguang Li;  Yan Huang;  Liang Wang;  Tieniu Tan;  Jing Shao
Adobe PDF(1722Kb)  |  Favorite  |  View/Download:11/0  |  Submit date:2024/05/28
Constrained-cost adaptive dynamic programming for optimal control of discrete-time nonlinear systems 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 卷号: 35, 期号: 3, 页码: 3251 - 3264
Authors:  Wei, Qinglai;  Li, Tao
Adobe PDF(8471Kb)  |  Favorite  |  View/Download:3/1  |  Submit date:2024/05/28
Adaptive dynamic programming  approximate dynamic programming  constrained cost  optimal control  reinforcement learning