SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
This study unveils the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments, and proposes a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability.
Oubo Ma, Yuwen Pu, L. Du et al.
· Conference on Computer and C... · 16 citations