中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共137条，第1-10条 帮助

限定条件                
已选(0)清除 条数/页：   排序方式：
MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts 会议论文
, Torino (Italia), 2024.5.20 - 2024.5.25
作者:  Xiang Li;  Shizhu He;  Jiayu Wu;  Zhao Yang;  Yao Xu;  Yang Jun;  Haifeng Liu;  Kang Liu;  Jun Zhao
Adobe PDF(1062Kb)  |  收藏  |  浏览/下载：32/8  |  提交时间：2024/06/20
Teaching Small Language Models to Reason for Knowledge-Intensive Multi-Hop Question Answering 会议论文
, Bangkok, Thailand, 2024.08.11-2024.08.16
作者:  Xiang Li;  Shizhu HE;  Fangyu Lei;  Jun Yang;  Tianhuang Su;  Kang Liu;  Jun Zhao
Adobe PDF(873Kb)  |  收藏  |  浏览/下载：40/14  |  提交时间：2024/06/20
Advancing Air Combat Tactics with Improved Neural Fictitious Self-Play Reinforcement Learning 会议论文
Advanced Intelligent Computing Technology and Applications, 中国郑州, 2023-8
作者:  He SQ(何少钦);  Gao Y(高阳);  Zhang BF(张保丰);  Chang H(常惠);  Zhang XC(张鑫辰)
Adobe PDF(1496Kb)  |  收藏  |  浏览/下载：60/21  |  提交时间：2024/05/31
Air Combat, Reinforcement Learning, Neural Fictitious Self-Play.  
CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge 会议论文
, Virtual Event, 2021-2
作者:  Wang, Chenhao;  Chen, Yubo;  Xue, Zhipeng;  Zhou, Yang;  Zhao, Jun
Adobe PDF(366Kb)  |  收藏  |  浏览/下载：36/13  |  提交时间：2024/05/30
Explicitly Learning Policy Under Partial Observability in Multiagent Reinforcement Learning 会议论文
, Queensland, Australia, 2023-6
作者:  Yang, Chen;  Yang, Guangkai;  Chen, Hao;  Zhang, Junge
Adobe PDF(3027Kb)  |  收藏  |  浏览/下载：60/22  |  提交时间：2024/05/29
Integrated Tracking Control of an Underwater Bionic Robot Based on Multimodal Motions 期刊论文
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, 卷号: 54, 期号: 3, 页码: 1599-1610
作者:  Wang, Jian;  Wu, Zhengxing;  Zhang, Yang;  Kong, Shihan;  Tan, Min;  Yu, Junzhi
Adobe PDF(5090Kb)  |  收藏  |  浏览/下载：97/20  |  提交时间：2024/03/27
Disturbance observer (DOB)  fuzzy system  model predictive control (MPC)  tracking control  underwater bionic robot  
Enhancing Short Track Speed Skating Performance through Improved DDQN Tactical Decision Model 期刊论文
SENSORS, 2023, 卷号: 23, 期号: 24, 页码: 12
作者:  Yang, Yuanbo;  Li, Feimo;  Chang, Hongxing
收藏  |  浏览/下载：46/0  |  提交时间：2024/02/22
short track speed skating  deep reinforcement learning  decision-making method  deep Q-network  competition performance improvement  
A Novel Underwater Image Synthesis Method Based on a Pixel-level Self-Supervised Training Strategy 会议论文
, Xining, China, 2021-7
作者:  Zhiheng Wu;  Zhengxing Wu;  Yue Lu;  Jian Wang;  Junzhi Yu
Adobe PDF(1862Kb)  |  收藏  |  浏览/下载：153/53  |  提交时间：2023/06/29
一种支持图灵测试模式的人机对抗系统及智能体测试方法 专利
专利类型: 发明专利, 专利号: CN202111328333.3, 申请日期: 2022-01-01,
发明人:  倪晚成;  徐佳乐;  王士贤;  黄凯奇;  杨旭阳
Adobe PDF(507Kb)  |  收藏  |  浏览/下载：175/55  |  提交时间：2023/06/28
Commander-Soldiers Reinforcement Learning for Cooperative Multi-Agent Systems 会议论文
, 意大利, 2022-7
作者:  Chen YQ(陈逸群);  Yang Wei;  Tianle Zhang;  Shiguang Wu;  Hongxing Chang
Adobe PDF(15907Kb)  |  收藏  |  浏览/下载：167/36  |  提交时间：2023/06/28