CASIA OpenIR

Browse/Search Results:  1-10 of 10 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
基于深度强化学习的群体协同决策方法研究 学位论文
工学博士, 中国科学院自动化研究所: 中国科学院自动化研究所, 2022
Authors:  吴士广
Adobe PDF(14260Kb)  |  Favorite  |  View/Download:93/7  |  Submit date:2022/06/15
群体系统  协同决策  深度强化学习  多智能体强化学习  图注意力网络  
Attention Enhanced Reinforcement Learning for Multi agent Cooperation 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 15
Authors:  Pu, Zhiqiang;  Wang, Huimu;  Liu, Zhen;  Yi, Jianqiang;  Wu, Shiguang
Adobe PDF(2967Kb)  |  Favorite  |  View/Download:41/4  |  Submit date:2022/06/06
Training  Reinforcement learning  Games  Scalability  Task analysis  Standards  Optimization  Attention mechanism  deep reinforcement learning (DRL)  graph convolutional networks  multi agent systems  
Deep reinforcement learning based multi-target coverage with connectivity guaranteed 期刊论文
IEEE Transactions on Industrial Informatics, 2022, 期号: 2022, 页码: 1-12
Authors:  Shiguang Wu;  Zhiqiang Pu;  Tenghai Qiu;  Jianqiang Yi;  Tianle Zhang
Adobe PDF(15731Kb)  |  Favorite  |  View/Download:39/3  |  Submit date:2022/04/02
Multi-target coverage  multi-robot system  connectivity maintenance  deep reinforcement learning  
Multi-agent Collaborative Learning with Relational Graph Reasoning in Adversarial Environments 会议论文
, 线上会议, 2021-9
Authors:  Wu Shiguang;  Qiu Tenghai;  Pu Zhiqiang;  Yi Jianqiang
Adobe PDF(1396Kb)  |  Favorite  |  View/Download:19/2  |  Submit date:2022/06/16
Formation control with collision avoidance through deep reinforcement learning using model-guided demonstration 期刊论文
IEEE Transactions on Neural Networks and Learning Systems, 2021, 卷号: 32, 期号: 6, 页码: 2358-2372
Authors:  Zezhi Sui;  Zhiqiang Pu;  Jianqiang Yi;  Shiguang Wu
Adobe PDF(5344Kb)  |  Favorite  |  View/Download:26/7  |  Submit date:2022/04/02
Collision avoidance  deep reinforcement learning (DRL)  formation control  leader–follower  
Multi-target Coverage with Connectivity Maintenance using Knowledge-incorporated Policy Framework 会议论文
, Xi'an China, May 31-Jun. 4
Authors:  Shiguang Wu;  Zhiqiang Pu;  Zhen Liu;  Tenghai Qiu;  Jianqiang Yi;  Tianle Zhang
Adobe PDF(12862Kb)  |  Favorite  |  View/Download:17/4  |  Submit date:2022/04/06
Multi-Agent Cooperation and Competition with Two-Level Ggraph Attention Network 会议论文
, 线上, 2020-11
Authors:  Shiguang, Wu;  Zhiqiang, Pu;  Jianqiang, Yi;  Huimu, Wang
Adobe PDF(1185Kb)  |  Favorite  |  View/Download:50/1  |  Submit date:2021/06/24
Multi-robot cooperative target encirclement through learning distributed transferable policy 会议论文
, Online, July 19-24
Authors:  Zhang Tianle;  Liu Zhen;  Wu Shiguang;  Pu Zhiqiang;  Yi Jianqiang
Adobe PDF(949Kb)  |  Favorite  |  View/Download:17/3  |  Submit date:2022/06/16
Adaptive flocking of multi-agent system with uncertain nonlinear dynamics and unknown disturbances using neural networks 会议论文
, Online, August 20-21
Authors:  Shiguang Wu;  Zhiqiang Pu;  Jianqiang Yi;  Jinlin Su;  Tianyi Xiong;  Tenghai Qiu
Adobe PDF(2014Kb)  |  Favorite  |  View/Download:13/1  |  Submit date:2022/04/06
A hybrid formation control design for multi-robot system with obstacle avoidance 会议论文
, Guangzhou, July 27-30
Authors:  Wu Shiguang;  Sui Zezhi;  Yi Jianqiang;  Pu Zhiqiang
Adobe PDF(751Kb)  |  Favorite  |  View/Download:10/1  |  Submit date:2022/06/16