Research map / Multi-agent systems and games / Cooperative multi-agent RL
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
Sunwoo Lee, Mingu Kang, Yonghyeon Jo, Seungyul Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use zero-masking instead of Gaussian noise on MI-selected dimensions (ablation) | IBAL · SMAC 8m, Dis-1 | win rate (%): 78.1 -> 88.4 | Improved |
| use zero-masking instead of FGSM on MI-selected dimensions (ablation) | IBAL · SMAC 8m, Dis-1 | win rate (%): 38.5 -> 88.4 | Improved |
| use zero-masking instead of Gaussian noise (ablation) | IBAL · SMAC MMM, Dis-1 | win rate (%): 71.9 -> 88.7 | Improved |
| use zero-masking instead of FGSM (ablation) | IBAL · SMAC MMM, Dis-1 | win rate (%): 77.6 -> 88.7 | Improved |
| add observation attack to the action attack (ablation) | IBAL · SMAC 8m, Dis-1 | win rate | Improved |
| add action attack to the observation attack (ablation) | IBAL · SMAC 8m, Dis-1 | win rate | Improved |
| use MI-guided masking instead of random masking (ablation) | IBAL · SMAC 8m, Dis-1 | win rate | Improved |
| use adaptive attack probability instead of fixed 1/K (ablation) | IBAL · SMAC 8m, Dis-1 | win rate | Improved |
| increase maximum group size K (ablation) | IBAL · SMAC 2s3z and 8m, Dis-1 | win rate: K=1 best on 2s3z; 8m stable up to K=4 | Mixed |
Closest papers by meaning
- Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.90)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.89)
- Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game (ICLR 2024 · similarity 0.88)
- AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning (ICML 2026 · similarity 0.88)
- Robust Multi-Agent Reinforcement Learning with Stochastic Adversary (ICML 2025 · similarity 0.88)
- Robust Communicative Multi-Agent Reinforcement Learning with Active Defense (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
