Research map / Multi-agent systems and games / Cooperative multi-agent RL
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Zheng Yuwei, Linhao Wang, Ruixiao Xu, Chengdong Ma, Zhiqian Liu, Xin Yu, Yuqing Ma, Xin Wang, Jie Luo, Bo An and 3 more
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 VAI (Bellman-operator value reward) instead of baseline selectors | vulnerable agent selection · Battle/Taxi/Vicsek, 18 tasks | system reward under attack: outperforms all baselines in 17 out of 18 tasks | Improved |
| use degree centrality or PIANO instead of random selection | vulnerable agent selection · Battle/Taxi/Vicsek | system reward under attack | No clear effect |
| use dense reward from the regularized Bellman value instead of sparse bi-level RL reward (ablation) | upper-level selection · Battle/Taxi/Vicsek | system reward under attack: Battle 64/8: 295.09 (Bi-level) -> 281.50 (VAI-RL) | Improved |
| use RL instead of greedy for upper-level selection (ablation) | VAI · Battle/Taxi/Vicsek, 18 tasks | system reward under attack: VAI-RL better in 10 of 18 tasks | Mixed |
| use the Bellman-operator value as predictor of RL-trained attack result | regularized mean-field Bellman operator · Battle 64 agents | Pearson correlation: r = 0.97 | Improved |
| add more rollouts for training the value function (ablation) | VAI step 1 · pilot study | performance | No clear effect |
Closest papers by meaning
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.87)
- AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning (ICML 2026 · similarity 0.87)
- Robust Multi-Agent Reinforcement Learning with Stochastic Adversary (ICML 2025 · similarity 0.87)
- Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game (ICLR 2024 · similarity 0.86)
- Major-Minor Mean Field Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.86)
- Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL (ICLR 2024 · similarity 0.85)
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.
