mlsanityData to 7 Oct 2026

Sparse Adversarial Attack in Multi-agent Reinforcement Learning

arXiv 2205.09362 ↗First posted 19 May 2022cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Cooperative multi-agent reinforcement learning (cMARL) has many real applications, but the policy trained by existing cMARL algorithms is not robust enough when deployed. There exist also many methods about adversarial attacks on the RL system, which implies that the RL system can suffer from adversarial attacks, but most of them focused on single agent RL. In this paper, we propose a textitsparse adversarial attack on cMARL systems. We use (MA)RL with regularization to train the attack policy. Our experiments show that the policy trained by the current cMARL algorithm can obtain poor performance when only one or a few agents in the team (e.g., 1 of 8 or 5 of 25) were attacked at a few timesteps (e.g., attack 3 of total 40 timesteps).

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 19 May 2022.

Builds on

27 of 38 references.

References · 27

  1. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  2. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  3. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  4. 2019The StarCraft Multi-Agent Challengecited by 589
  5. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 490
  6. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  7. 2017Adversarial Attacks on Neural Network Policiescited by 314
  8. 2016Safe, Multi-Agent, Reinforcement Learning for Autonomous Drivingcited by 301
  9. 2020Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 197
  10. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
  11. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  12. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
15 more
  1. 2019Robust Reinforcement Learning for Continuous Control with Model Misspecificationcited by 76
  2. 2018Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networkscited by 70
  3. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  4. 2019Wasserstein Robust Reinforcement Learningcited by 50
  5. 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
  6. 2019Characterizing Attacks on Deep Reinforcement Learningcited by 31
  7. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 24
  8. 2019Optimal Attacks on Reinforcement Learning Policiescited by 21
  9. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  10. 2021ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxationcited by 17
  11. 2018Sequential Attacks on Agents for Long-Term Adversarial Goalscited by 16
  12. 2020Robust Constrained Reinforcement Learning for Continuous Control with Model Misspecificationcited by 16
  13. 2019Adversarial Exploitation of Policy Imitationcited by 13
  14. 2020Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learningcited by 13
  15. 2021Robust Reinforcement Learning under model misspecificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 0; 2025: 1; 2026: 2.

8 papers.

  1. 2023Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackerscited by 15
  2. 2023Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generationcited by 6
  3. 2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
  4. 2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
  5. 2023Enhancing the Robustness of QMIX against State-adversarial Attackscited by 3
  6. 2025Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learningcited by 0
  7. 2026Detection of adversarial intent in Human-AI teams using LLMscited by 0
  8. 2026When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learningcited by 0