arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08975cs.MAcs.LG
收藏

基于通信的多智能体深度强化学习综述

A Survey of Multi-Agent Deep Reinforcement Learning with Communication

Utrecht University(乌得勒支大学)

Changxi Zhu, Mehdi Dastani, Shihan Wang

AI总结:

本文综述了基于通信的多智能体深度强化学习研究,提出9个分析维度对现有方法进行分类比较,并探讨未来系统设计的新方向。

摘要:

通信是协调多个智能体行为、拓宽其对环境的认知并支持它们协作的有效机制。在多智能体深度强化学习(MADRL)领域,智能体可以通过通信提升整体学习性能并实现各自目标。智能体可以传递多种类型的消息,既可以面向所有智能体,也可以面向特定智能体组,或者受特定条件约束。随着基于通信的多智能体深度强化学习(Comm-MADRL)研究工作的不断增多,目前缺乏一种系统化、结构化的方法来区分和分类现有的Comm-MADRL方法。本文综述了Comm-MADRL领域的最新工作,并考虑了在设计和开发多智能体强化学习系统中可能发挥作用的通信的各个方面。基于这些方面,我们提出了9个维度,可据此对Comm-MADRL方法进行分析、开发和比较。通过将现有工作投影到多维空间中,我们发现了一些有趣的趋势。我们还通过探索这些维度的可能组合,为设计未来的Comm-MADRL系统提出了一些新的方向。

英文摘要:

Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication. Agents can communicate various types of messages, either to all agents or to specific agent groups, or conditioned on specific constraints. With the growing body of research work in MADRL with communication (Comm-MADRL), there is a lack of a systematic and structural approach to distinguish and classify existing Comm-MADRL approaches. In this paper, we survey recent works in the Comm-MADRL field and consider various aspects of communication that can play a role in designing and developing multi-agent reinforcement learning systems. With these aspects in mind, we propose 9 dimensions along which Comm-MADRL approaches can be analyzed, developed, and compared. By projecting existing works into the multi-dimensional space, we discover interesting trends. We also propose some novel directions for designing future Comm-MADRL systems through exploring possible combinations of the dimensions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑