CASIA OpenIR

Browse/Search Results:  1-10 of 117 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
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
FOV Constraint Region Analysis and Path Planning for Mobile Robot with Observability to Multiple Feature Points 期刊论文
International Journal of Control, Automation and Systems, 2021, 卷号: 19, 期号: 11, 页码: 3785-3800
Authors:  Hongxuan Ma;  Wei Zou;  Siyang Sun;  Zheng Zhu;  Zhaobing Kang
Adobe PDF(6468Kb)  |  Favorite  |  View/Download:34/12  |  Submit date:2024/06/06
mobile robot  multiple points  path planning  the field-of-view  
FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game 期刊论文
IEEE Transactions on Emerging Topics in Computational Intelligence, 2024, 页码: 1-13
Authors:  Guangzheng Hu;  Yuanheng Zhu;  Haoran Li;  Dongbin Zhao
Adobe PDF(2144Kb)  |  Favorite  |  View/Download:34/5  |  Submit date:2024/06/05
Games  Q-learning  Task analysis  Optimization  Convergence  Training  Nash equilibrium  Multi-agent reinforcement learning  minimax-Q learning  two-team zero-sum Markov games  
An Empirical Study on Google Research Football Multi-agent Scenarios 期刊论文
Machine Intelligence Research, 2024, 卷号: 21, 期号: 3, 页码: 549-570
Authors:  Yan Song;  He Jiang;  Zheng Tian;  Haifeng Zhang;  Yingping Zhang;  Jiangcheng Zhu;  Zonghong Dai;  Weinan Zhang;  Jun Wang
Adobe PDF(24588Kb)  |  Favorite  |  View/Download:50/12  |  Submit date:2024/05/23
Multi-agent reinforcement learning (RL), distributed RL system, population-based training, reward shaping, game theory  
一种基于目标空间转换权重求和的超多目标进化算法 期刊论文
自动化学报, 2022, 卷号: 48, 期号: 4, 页码: 1060-1078
Authors:  梁正平;  骆婷婷;  王志强;  朱泽轩;  胡凯峰
Adobe PDF(7389Kb)  |  Favorite  |  View/Download:39/14  |  Submit date:2024/05/20
目标空间转换  权重求和  超多目标优化  进化算法  
基于旋转框精细定位的遥感目标检测方法研究 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 2, 页码: 415-424
Authors:  朱煜;  方观寿;  郑兵兵;  韩飞
Adobe PDF(10493Kb)  |  Favorite  |  View/Download:21/9  |  Submit date:2024/05/09
遥感图像  旋转框检测  两阶段调整  像素重组金字塔  区域特征提取  
基于剪枝堆栈泛化的离线数据驱动进化优化 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 6, 页码: 1306-1325
Authors:  梁正平;  黄锡均;  李燊钿;  王喜瑜;  朱泽轩
Adobe PDF(2386Kb)  |  Favorite  |  View/Download:47/15  |  Submit date:2024/05/09
堆栈泛化  代理模型  离线数据驱动优化  进化计算  
自适应变化响应的动态多目标进化算法 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 8, 页码: 1688-1706
Authors:  梁正平;  李辉才;  王志强;  胡凯峰;  朱泽轩
Adobe PDF(6886Kb)  |  Favorite  |  View/Download:56/21  |  Submit date:2024/04/24
动态多目标优化  进化算法  自适应变化响应  预测  存档  
数据驱动的间歇低氧训练贝叶斯优化决策方法 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 8, 页码: 1667-1678
Authors:  陈婧;  史大威;  蔡德恒;  王军政;  朱玲玲
Adobe PDF(6031Kb)  |  Favorite  |  View/Download:39/13  |  Submit date:2024/04/24
数据驱动控制  高斯过程  贝叶斯优化  风险不对称代价函数  高原适应能力提升  间歇性低氧训练  
EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training 期刊论文
Machine Intelligence Research, 2023, 卷号: 20, 期号: 2, 页码: 207-219
Authors:  Yuxian Gu;  Jiaxin Wen;  Hao Sun;  Yi Song;  Pei Ke;  Chujie Zheng;  Zheng Zhang;  Jianzhu Yao;  Lei Liu;  Xiaoyan Zhu;  Minlie Huang
Adobe PDF(1846Kb)  |  Favorite  |  View/Download:43/15  |  Submit date:2024/04/23
Natural language processing  deep learning (DL)  large-scale pre-training  dialogue systems  Chinese open-domain conversational model