Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Sunwoo, Kang, Mingu, Jo, Yonghyeon, Han, Seungyul
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916063571083264
author Lee, Sunwoo
Kang, Mingu
Jo, Yonghyeon
Han, Seungyul
author_facet Lee, Sunwoo
Kang, Mingu
Jo, Yonghyeon
Han, Seungyul
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
Lee, Sunwoo
Kang, Mingu
Jo, Yonghyeon
Han, Seungyul
Machine Learning
Artificial Intelligence
Multiagent Systems
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.
title Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2605.18024