SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

no code implementations • 6 Feb 2024 • Oubo Ma, Yuwen Pu, Linkang Du, Yang Dai, Ruo Wang, Xiaolei Liu, Yingcai Wu, Shouling Ji

Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

Multi-agent Reinforcement Learning