ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation

Understand

In a multirobot system, a number of cyber-physical attacks (e.g., communication hijack, observation perturbations) can challenge the robustness of agents.

• This robustness issue worsens in multiagent reinforcement learning because there exists the non-stationarity of the environment caused by simultaneously learning agents whose changing policies affect the transition and reward functions.
• In this paper, we propose a minimax MARL approach to infer the worst-case policy update of other agents.
• As the minimax formulation is computationally intractable to solve, we apply the convex relaxation of neural networks to solve the inner minimization problem.