mlsanityData to 7 Oct 2026

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

arXiv 2306.06136 ↗First posted 9 Jun 2023cs.LG cs.AI cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Multi-Agent Reinforcement Learning (MARL) has been widely applied in many fields such as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are vulnerable to adversarial perturbations on agent states. Robustness testing for a trained model is an essential step for confirming the trustworthiness of the model against unexpected perturbations. This work proposes a novel Robustness Testing framework for MARL that attacks states of Critical Agents (RTCA). The RTCA has two innovations: 1) a Differential Evolution (DE) based method to select critical agents as victims and to advise the worst-case joint actions on them; and 2) a team cooperation policy evaluation method employed as the objective function for the optimization of DE. Then, adversarial state perturbations of the critical agents are generated based on the worst-case joint actions. This is the first robustness testing framework with varying victim agents. RTCA demonstrates outstanding performance in terms of the number of victim agents and destroying cooperation policies.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 23 of its 38 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

23 of 38 references.

References · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  5. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  6. 2019The StarCraft Multi-Agent Challengecited by 589
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  9. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  10. 2017Adversarial Attacks on Neural Network Policiescited by 314
  11. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  12. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
11 more
  1. 2013The Complexity of Decentralized Control of Markov Decision Processescited by 225
  2. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  3. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
  4. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  5. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
  6. 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
  7. 2020Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computingcited by 22
  8. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  9. 2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 21
  10. 2022RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on statescited by 16
  11. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertaintycited by 24
  2. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learningcited by 12
  3. 2025Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learningcited by 0
  4. 2025SAJA: A State-Action Joint Attack Framework on Multi-Agent Deep Reinforcement Learningcited by 0
  5. 2026Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorizationcited by 0
  6. 2026Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policiescited by 0
  7. 2026Evaluating Fuzz Testing for Reinforcement Learning Agentscited by 0