面向多智能体协作的注意力意图与交流学习方法

俞文武, 杨晓亚, 李海昌, 王瑞, 胡晓惠 - 自动化学报, 2023 - aas.net.cn
… Abstract: For multi-agent communication and cooperation tasks in partially … multi-agent
attentional intention communication (MAAIC) algorithm is proposed to improve the communication

[PDF][PDF] 基于通信的多智能体强化学习进展综述

王涵, 俞扬, 姜远 - 中国科学: 信息科学, 2022 - scis.scichina.com
… (multi-agent reinforcement learning, MARL) 为技术手段, 应对现实的复杂系统. 近十年来, 多
智能体系统(multiagentTarMAC: targeted multi-agent communication. In: Proceedings of the …

[HTML][HTML] 部分可观测下基于RGMAAC 算法的多智能体协同

王子豪, 张严心, 黄志清, 殷辰堃 - 2023 - kzyjc.alljournals.cn
… algorithm Actor-Critic to multi-agent systems and adds communication channels and gating
… gated multi-agent Actor-Critic (RGMAAC) algorithm. Agents can communicate efficiently …

深度强化学习算法与应用研究现状综述

刘朝阳, 穆朝絮, 孙长银 - 智能科学与技术学报, 2020 - infocomm-journal.com
… games, navigation, multi-agent cooperation and recommendation field … Learning to schedule
communication in multi-agentTarMAC: targeted multi-agent communication[C]//The 36th …

部分可观测条件下的策略迁移强化学习方法

王忠禹, 徐晓鹏, 王东 - 现代防御技术, 2024 - xdfyjs.cn
… Abstract:Multi-agent reinforcement learning algorithms fail to form effective collaborative
policy under partially observable conditions. In view of this problem,a policy transfer …

面向有人/无人协同的智能通信与组网关键技术: 现状与趋势

尹浩, 魏急波, 赵海涛, 张姣, 王海军, 任保全 - 通信学报, 2024 - infocomm-journal.com
communication and networking technologies for manned/unmanned cooperation was
comprehensively surveyed. Firstly, the requirements on communication … 学习(MARL, multi-agent

[HTML][HTML] 强化学习与自适应动态规划: 从基础理论到多智能体系统中的应用进展综述

温广辉, 杨涛, 周佳玲, 付俊杰, 徐磊 - 控制与决策, 2023 - kzyjc.alljournals.cn
… coordination control problem of multi-agent systems is reviewed. … control problem of multi-agent
systems are suggested. … 智能体激励沟通(multi-agent incentive communication, MAIC)框架…