Research map / Multi-agent systems and games / Cooperative multi-agent RL
Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
Alexander Bukharin, Yan Li, Yue Yu, Qingru Zhang, Zhehui Chen, Simiao Zuo, Chao Zhang, Songan Zhang, Tuo Zhao
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 |
|---|---|---|---|
| add ERNIE adversarial regularization | COMA · Traffic light, training env | reward: -93.97 -> -78.39 | Improved |
| add ERNIE adversarial regularization | COMA · Traffic light, obs noise 1.0 | reward: -113.24 -> -102.45 | Improved |
| add ERNIE adversarial regularization | COMA · Traffic light, speed 30 m/s | reward: -108.45 -> -91.73 | Improved |
| add ERNIE adversarial regularization | QCOMBO · Traffic light 6x6 grid | reward: -320.66 -> -152.60 | Improved |
| add ERNIE adversarial regularization | QCOMBO · Traffic light Atlanta network | reward: -435.69 -> -285.84 | Improved |
| add ERNIE adversarial regularization | COMA · Traffic light 4x4 grid | reward: -384.17 -> -394.14 | Hurt |
| add ERNIE adversarial regularization | COMA · Traffic light 6x6 grid | reward: -330.55 -> -337.25 | Hurt |
| add Stackelberg training to adversarial regularization (ablation) | ERNIE · Traffic light, COMA training env | reward: -83.07 -> -78.39 | Improved |
| add Stackelberg training to adversarial regularization (ablation) | ERNIE · Traffic light 6x6 grid, QCOMBO | reward: -213.20 -> -152.60 | Improved |
| add Stackelberg training to adversarial regularization (ablation) | ERNIE · Traffic light Atlanta, QCOMBO | reward: -339.48 -> -285.84 | Improved |
| add Stackelberg training to adversarial regularization (ablation) | ERNIE · Traffic light 6x6 grid, COMA | reward: -319.16 -> -337.25 | Hurt |
| add Stackelberg training to adversarial regularization (ablation) | ERNIE · Traffic light Atlanta, COMA | reward: -402.12 -> -432.87 | Hurt |
Closest papers by meaning
- Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula (ICLR 2024 · similarity 0.89)
- Robust Multi-Agent Reinforcement Learning with Stochastic Adversary (ICML 2025 · similarity 0.89)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.88)
- Adversarial Diffusion for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation (NeurIPS 2026 · similarity 0.88)
- Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks (AAAI 2024 · similarity 0.88)
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.
