arXiv：cs.AI（全量分类）· Huiwen Yan, Kyriakos G. Vamvoudakis, Mushuang Liu·· 5 小时前AI 评分27
Meta-MARL：面向交互策略快速适应的元多智能体强化学习框架及自动驾驶应用
Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving
AI 导读
研究者提出 meta-MARL 框架，将多智能体强化学习建模为 Markov 博弈，实现跨博弈分布的交互策略快速适应，并定义新解概念 meta-NE，证明其与基于 gradient-play 的 meta-MARL 算法稳定点的等价充分条件。在自动驾驶任务上，该方法比预训练 MARL 基线适应更快。
正文
Abstract:This paper develops a meta-multi-agent reinforcement learning (meta-MARL) framework to enable fast adaptation of interactive policies in a multi-agent system (MAS). Meta-reinforcement learning (meta-RL) enables agents to rapidly adapt to new tasks/environments using a bi-level optimization mechanism. However, existing meta-RL generally focuses on single-agent systems. Extending these frameworks and algorithms to multi-agent systems poses additional challenges, as tasks are characterized by not only the environment but also agents' strategic interactions. To address these challenges, we model multi-agent reinforcement learning (MARL) problems as Markov games (MGs) and develop a meta-MARL framework for rapid interactive policy adaptation across a distribution of MGs. A new concept, called meta-NE, is defined to describe the desired solution concept in a meta-MARL problem. Sufficient conditions for the equivalence between a meta-NE and a stationary point of the gradient-play-based meta-MARL algorithm are established. Our evaluation on autonomous-driving tasks demonstrates that the proposed meta-MARL method achieves faster adaptation than pretrained MARL baselines, validating the effectiveness of our framework.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Systems and Control (eess.SY) |
| Cite as: | arXiv:2610.00705 [cs.AI] |
| (or arXiv:2610.00705v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00705 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Huiwen Yan [view email]
[v1]
Wed, 30 Sep 2026 20:52:19 UTC (2,222 KB)
来源：arXiv：cs.AI（全量分类） · arxiv.org