Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (6): 1457-1475.DOI: 10.3778/j.issn.1673-9418.2312006

• Frontiers·Surveys • Previous Articles     Next Articles

Review of Attention Mechanisms in Reinforcement Learning

XIA Qingfeng, XU Ke'er, LI Mingyang, HU Kai, SONG Lipeng, SONG Zhiqiang, SUN Ning   

  1. 1. School of Automation, Wuxi University, Wuxi, Jiangsu 214105, China
    2. School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • Online:2024-06-01 Published:2024-05-31

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   

  1. 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

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.

Key words: reinforcement learning, attention mechanism, multi-agent system

摘要: 近年来,强化学习与注意力机制的结合在算法研究领域备受瞩目。在强化学习算法中,注意力机制的应用在提高算法性能方面发挥了重要作用。重点聚焦于注意力机制在深度强化学习中的发展,审视了其在多智能体强化学习领域的应用,并对相关研究成果进行调研。首先,介绍了注意力机制和强化学习的研究背景与发展历程,并调研了该领域中的相关实验平台;然后,回顾了强化学习与注意力机制的经典算法,并从不同角度对注意力机制进行分类;接着,对注意力机制在强化学习领域的应用进行了梳理,根据三种任务类型(完全合作型、完全竞争型和混合合作竞争型)进行分类分析,重点关注了多智能体领域的应用情况;最后,总结了注意力机制对强化学习算法的改进作用,并展望了该领域所面临的挑战和未来的研究前景。

关键词: 强化学习, 注意力机制, 多智能体系统