mlsanityData to 14 Oct 2026

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

arXiv 2605.18024 ↗First posted 18 May 2026cs.LG cs.AI cs.MAcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 76 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

44 of 76 references.

References · 44

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2019The StarCraft Multi-Agent Challengecited by 597
  3. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  4. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  5. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  6. 2017Robust Adversarial Reinforcement Learningcited by 451
  7. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
  8. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
  9. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 235
  10. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  11. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  12. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
32 more
  1. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 154
  2. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  3. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  4. 2021Celebrating Diversity in Shared Multi-Agent Reinforcement Learningcited by 98
  5. 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 61
  6. 2021Adversarial Attacks On Multi-Agent Communicationcited by 49
  7. 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
  8. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 36
  9. 2020Robustifying Reinforcement Learning Agents via Action Space Adversarial Trainingcited by 30
  10. 2021A Max-Min Entropy Framework for Reinforcement Learningcited by 28
  11. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  12. 2022Cooperative Multi-Agent Deep Reinforcement Learning for Reliable Surveillance via Autonomous Multi-UAV Controlcited by 26
  13. 2022Robust Imitation Learning against Variations in Environment Dynamicscited by 26
  14. 2023Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithmscited by 25
  15. 2022PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaborationcited by 23
  16. 2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 22
  17. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  18. 2021Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learningcited by 18
  19. 2023Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Gamecited by 18
  20. 2020Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agentscited by 15
  21. 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
  22. 2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
  23. 2024Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Spacecited by 9
  24. 2021MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learningcited by 6
  25. 2023Robust Multi-Agent Reinforcement Learning by Mutual Information Regularizationcited by 6
  26. 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learningcited by 6
  27. 2025Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learningcited by 5
  28. 2023Noise Distribution Decomposition based Multi-Agent Distributional Reinforcement Learningcited by 4
  29. 2024Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agentscited by 3
  30. 2026Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learningcited by 3
  31. 2025Focusing Influence Mechanism for Multi-Agent Reinforcement Learningcited by 2
  32. 2026Shaping Zero-Shot Coordination via State Blockingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning
  2. 2024SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
  3. 2025Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
  4. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
  5. 2024CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
  6. 2024Multi-Agent Diagnostics for Robustness via Illuminated Diversity
  7. 2025Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
  8. 2025AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning