| 注册
首页|期刊导航|计算机科学与探索|强化学习中的注意力机制研究综述

强化学习中的注意力机制研究综述

夏庆锋 许可儿 李明阳 胡凯 宋利鹏 宋志强 孙宁

计算机科学与探索2024,Vol.18Issue(6):1457-1475,19.
计算机科学与探索2024,Vol.18Issue(6):1457-1475,19.DOI:10.3778/j.issn.1673-9418.2312006

强化学习中的注意力机制研究综述

Review of Attention Mechanisms in Reinforcement Learning

夏庆锋 1许可儿 2李明阳 2胡凯 2宋利鹏 2宋志强 1孙宁1

作者信息

  • 1. 无锡学院 自动化学院,江苏 无锡 214105
  • 2. 南京信息工程大学 自动化学院,南京 210044
  • 折叠

摘要

Abstract

In recent years,the combination of reinforcement learning and attention mechanisms has attracted an increasing attention in algorithmic research field.Attention mechanisms play an important role in improving the performance of algorithms in reinforcement learning.This paper mainly focuses on the development of attention mechanisms in deep reinforcement learning and examining their applications in the multi-agent reinforcement learning domain.Relevant researches are conducted accordingly.Firstly,the background and development of attention mechanisms and reinforcement learning are introduced,and relevant experimental platforms in this field are also presented.Secondly,classical algorithms of reinforcement learning and attention mechanisms are reviewed and attention mechanism is categorized from different perspectives.Thirdly,practical applications of attention mechanisms in the reinforcement field are sorted out based on three types of tasks including fully cooperative,fully competitive and mixed,with focus on the application in the field of multi-agent.Finally,the improvement of attention mechanisms on reinforcement learning algorithms is summarized.The challenges and future prospects in this field are discussed.

关键词

强化学习/注意力机制/多智能体系统

Key words

reinforcement learning/attention mechanism/multi-agent system

分类

信息技术与安全科学

引用本文复制引用

夏庆锋,许可儿,李明阳,胡凯,宋利鹏,宋志强,孙宁..强化学习中的注意力机制研究综述[J].计算机科学与探索,2024,18(6):1457-1475,19.

基金项目

辽宁省科技厅机器人学国家重点实验室联合开放基金(2021-KF-22-19).This work was supported by the Joint Fund of Science&Technology Department of Liaoning Province and State Key Laboratory of Robotics(2021-KF-22-19). (2021-KF-22-19)

计算机科学与探索

OA北大核心CSTPCD

1673-9418

访问量0
|
下载量0
段落导航相关论文