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

Sunwoo Lee, Mingu Kang, Yonghyeon Jo, Seungyul Han
5/18/2026
cs.LGcs.AIcs.MA

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game

89% match1 repo142026

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

89% match1 repo112026

Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

86% match2023

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

86% match1 repo52024

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

86% match2023

Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents

86% match2023

Cite this paper

@article{lee2026interactionbreaking,
  title  = {Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning},
  author = {Sunwoo Lee and Mingu Kang and Yonghyeon Jo and Seungyul Han},
  year   = {2026},
  eprint = {2605.18024},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2605.18024v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2605.18024.svg)](https://codeofpaper.com/paper/2605.18024)

Discussion