CASIA OpenIR

Browse/Search Results:  1-10 of 4029 Help

Selected(0)Clear Items/Page:    Sort:
Improved Self-Propelled Swarms Model with Enhanced Convergence Efficiency 会议论文
, Tianjing, China, 2020
Authors:  Boyin Liu;  Zhiqiang Pu;  Shiguang Wu;  Lele Wang
Adobe PDF(210Kb)  |  Favorite  |  View/Download:9/4  |  Submit date:2024/07/12
基于深度强化学习的足球智能体球员策略方法研究 学位论文
, 2024
Authors:  刘博寅
Adobe PDF(11380Kb)  |  Favorite  |  View/Download:7/0  |  Submit date:2024/07/12
足球  多智能体系统  深度强化学习  互信息  内在激励  预训练  
NExT-OOD: Overcoming Dual Multiple-Choice VQA Biases 期刊论文
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 页码: 1913-1931
Authors:  Zhang Xi(张熙);  Feifei Zhang;  Changsheng Xu
Adobe PDF(4719Kb)  |  Favorite  |  View/Download:20/5  |  Submit date:2024/07/08
Multi-Level Counterfactual Contrast for Visual Commonsense Reasoning 会议论文
, Chengdu, China, 2021-10
Authors:  Zhang X(张熙);  Feifei Zhang;  Changsheng Xu
Adobe PDF(5740Kb)  |  Favorite  |  View/Download:23/5  |  Submit date:2024/07/08
CGNN: A Compatibility-aware Graph Neural Network for Social Media Bot Detection 期刊论文
IEEE Transactions on Computational Social System, 2024, 页码: Early Access
Authors:  Huang, Haitao;  Tian, Hu;  Zheng, Xiaolong;  Zhang, Xingwei;  Zeng, Dajun;  Wang, Feiyue
Adobe PDF(2267Kb)  |  Favorite  |  View/Download:16/7  |  Submit date:2024/07/08
graph neural network  heterogeneous compatibility  social media bot detection  
基于异配图神经网络的社交机器人检测 学位论文
, 2024
Authors:  黄海涛
Adobe PDF(3065Kb)  |  Favorite  |  View/Download:11/0  |  Submit date:2024/07/08
社交机器人检测  图神经网络  异配性  相容性  图自监督学习  
面向多模态语义理解与推理的视觉问答研究 学位论文
, 2024
Authors:  张熙
Adobe PDF(39126Kb)  |  Favorite  |  View/Download:16/1  |  Submit date:2024/07/08
多模态  视觉问答  语义挖掘  可靠关联  推理泛化  
Learning State-Specific Action Masks for Reinforcement Learning 期刊论文
Algorithms, 2024, 卷号: 17, 期号: 2, 页码: 60
Authors:  Wang ZY(王梓薏);  Li XR(李欣然);  Sun LY(孙罗洋);  Zhang HF(张海峰);  Liu HL(刘华林);  Jun Wang
Adobe PDF(2976Kb)  |  Favorite  |  View/Download:19/8  |  Submit date:2024/07/05
reinforcement learning  exploration efficiency  space reduction  
NeuronsMAE: A Novel Multi-Agent Reinforcement Learning Environment for Cooperative and Competitive Multi-Robot Tasks 会议论文
, Queensland, Australia, 2023-6
Authors:  Hu GZ(胡光政);  Li HR(李浩然);  Liu SS(刘莎莎);  Zhu YH(朱圆恒);  Zhao DB(赵冬斌)
Adobe PDF(2785Kb)  |  Favorite  |  View/Download:28/7  |  Submit date:2024/07/04
面向多机器人博弈的深度强化学习方法 学位论文
, 2024
Authors:  胡光政
Adobe PDF(17740Kb)  |  Favorite  |  View/Download:21/0  |  Submit date:2024/07/04
多智能体深度强化学习  多机器人博弈  极小极大Q学习  值分解  最大熵