提出对抗学习框架，让多智能体在互动被破坏时仍能稳定协作。
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
- 从信息论出发，扰动观测与动作来破坏智能体间互动
- 在多种攻击场景下优于现有鲁棒MARL方法，缺智能体时也表现更强
- 适合研究多智能体系统抗干扰能力的学者
多智能体强化学习中，协作至关重要，但外部扰动可能破坏智能体间的交互，导致协调失效。已有鲁棒MARL方法主要关注价值导向攻击，对交互结构本身被破坏的情况缺乏应对。本文提出一种交互破坏性对抗学习（IBAL）框架，从信息论角度构建攻击：通过扰动智能体的观测与动作，破坏其协作机制，并训练智能体在这些干扰下仍能可靠运行。实验表明，该方法在多种攻击设置下均优于现有鲁棒MARL基线，在缺失智能体的情况下性能更优。代码已公开于 https://sunwoolee0504.github.io/IBAL。
原文摘要 · Abstract (English)
Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structures themselves are corrupted. In this paper, we propose an interaction-breaking adversarial learning (IBAL) framework that takes an information-theoretic view to construct attacks that impede coordination by perturbing agents' observations and actions, and trains agents to perform reliably under such disruptions. Empirically, our approach improves robustness over existing robust MARL baselines across diverse attack settings and yields stronger performance even under agent-missing scenarios. Our code is available at https://sunwoolee0504.github.io/IBAL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。