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 2510.17697cs.AIcs.LGcs.MA
收藏

多智能体强化学习中的定向干预原理

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

HKUST (GZ)(香港科技大学(广州));INFORMED-AI Hub(INFORMED-AI中心);University of Bristol(布里斯托大学);ELLIS Institute Finland(芬兰ELLIS研究所);Centre for Artificial Intelligence(人工智能中心);University College London(伦敦大学学院);School of Engineering Mathematics and Technology(工程数学与技术学院)

Anjie Liu, Jianhong Wang, Samuel Kaski, Jun Wang, Mengyue Yang

AI总结:

本文提出多智能体强化学习的定向干预范式,仅对单个目标智能体施加干预,并利用多智能体影响图和策略前干预(PSI)因果推断技术实现复合期望结果,以替代难以扩展的全局引导。

摘要:

将合作式多智能体强化学习(MARL)引导至期望结果具有挑战性,尤其是当在大规模MARL中由人对整个多智能体系统进行全局引导不切实际时。另一方面,设计外部机制(例如内在奖励和人类反馈)来协调智能体大多依赖经验研究,缺乏易于使用的研究工具。在本工作中,我们采用多智能体影响图(MAIDs)作为图形化框架来解决上述问题。首先,我们引入MARL交互范式的概念(与MARL学习范式正交),利用MAIDs分析和可视化MARL中无引导的自组织以及全局引导机制。然后,我们设计了一种新的MARL交互范式,称为定向干预范式,该范式仅应用于单个目标智能体,从而可以缓解全局引导问题。在实现上,我们引入一种因果推断技术,称为策略前干预(PSI),以实现定向干预范式。由于MAIDs可被视为因果图的一种特殊类别,通过PSI最大化相应因果效应,可以实现整合主任务目标与附加期望结果的复合期望结果。此外,MAIDs的捆绑相关图分析提供了一种工具,用于识别在某种MARL交互范式设计下,某种MARL学习范式是否可行。在实验中,我们证明了所提出的定向干预的有效性,并验证了相关图分析的结果。

英文摘要:

Steering cooperative multi-agent reinforcement learning (MARL) towards desired outcomes is challenging, particularly when the global guidance from a human on the whole multi-agent system is impractical in a large-scale MARL. On the other hand, designing external mechanisms (e.g., intrinsic rewards and human feedback) to coordinate agents mostly relies on empirical studies, lacking a easy-to-use research tool. In this work, we employ multi-agent influence diagrams (MAIDs) as a graphical framework to address the above issues. First, we introduce the concept of MARL interaction paradigms (orthogonal to MARL learning paradigms), using MAIDs to analyze and visualize both unguided self-organization and global guidance mechanisms in MARL. Then, we design a new MARL interaction paradigm, referred to as the targeted intervention paradigm that is applied to only a single targeted agent, so the problem of global guidance can be mitigated. In implementation, we introduce a causal inference technique, referred to as Pre-Strategy Intervention (PSI), to realize the targeted intervention paradigm. Since MAIDs can be regarded as a special class of causal diagrams, a composite desired outcome that integrates the primary task goal and an additional desired outcome can be achieved by maximizing the corresponding causal effect through the PSI. Moreover, the bundled relevance graph analysis of MAIDs provides a tool to identify whether an MARL learning paradigm is workable under the design of an MARL interaction paradigm. In experiments, we demonstrate the effectiveness of our proposed targeted intervention, and verify the result of relevance graph analysis.

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。

↑