arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.04850cs.AI
收藏

一种面向协作式多智能体学习问题的高效方法

An Efficient Approach for Cooperative Multi-Agent Learning Problems

Valencian Research Institute for AI (VRAIN)(瓦伦西亚人工智能研究院);Universitat Politècnica de València(瓦伦西亚理工大学)

Ángel Aso-Mollar, Eva Onaindia

AI总结:

本文提出一种集中式多智能体学习框架,通过引入监督者将联合动作抽象为顺序分配,以缓解动作空间爆炸问题,并在多种规模环境中验证了其协调能力与可扩展性。

摘要:

在本文中,我们提出了一种集中式多智能体学习框架,用于学习一个策略,该策略对需要协调以解决特定任务的多个智能体的同时行为进行建模。集中式方法通常面临动作空间爆炸的问题,该动作空间由所有可能的个体动作组合(即联合动作)定义。我们的方法通过一种顺序抽象来解决协调问题,从而克服了集中式方法典型存在的可扩展性问题。该方法引入了一个元智能体,称为“监督者(supervisor)”,它将联合动作抽象为向每个智能体依次分配动作的过程。这种顺序抽象不仅简化了集中式联合动作空间,还提升了框架的可扩展性和效率。我们的实验结果表明,所提出的方法能够在多种不同规模的多智能体学习环境中成功协调智能体。

英文摘要:

In this article, we propose a centralized Multi-Agent Learning framework for learning a policy that models the simultaneous behavior of multiple agents that need to coordinate to solve a certain task. Centralized approaches often suffer from the explosion of an action space that is defined by all possible combinations of individual actions, known as joint actions. Our approach addresses the coordination problem via a sequential abstraction, which overcomes the scalability problems typical to centralized methods. It introduces a meta-agent, called \textit{supervisor}, which abstracts joint actions as sequential assignments of actions to each agent. This sequential abstraction not only simplifies the centralized joint action space but also enhances the framework's scalability and efficiency. Our experimental results demonstrate that the proposed approach successfully coordinates agents across a variety of Multi-Agent Learning environments of diverse sizes.

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。

↑