Sparse Adversarial Attack in Multi-agent Reinforcement Learning
This addresses robustness issues in cMARL systems for real-world applications, but it is incremental as it extends adversarial attack concepts from single-agent to multi-agent settings.
The paper tackles the problem of adversarial attacks in cooperative multi-agent reinforcement learning (cMARL) by proposing a sparse adversarial attack method, showing that attacking only a few agents at limited timesteps (e.g., 1 of 8 or 5 of 25 agents, 3 of 40 timesteps) can significantly degrade policy performance.
Cooperative multi-agent reinforcement learning (cMARL) has many real applications, but the policy trained by existing cMARL algorithms is not robust enough when deployed. There exist also many methods about adversarial attacks on the RL system, which implies that the RL system can suffer from adversarial attacks, but most of them focused on single agent RL. In this paper, we propose a \textit{sparse adversarial attack} on cMARL systems. We use (MA)RL with regularization to train the attack policy. Our experiments show that the policy trained by the current cMARL algorithm can obtain poor performance when only one or a few agents in the team (e.g., 1 of 8 or 5 of 25) were attacked at a few timesteps (e.g., attack 3 of total 40 timesteps).