ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation
Chuangchuang Sun,Dong-Ki Kim,Jonathan P. How,Chuangchuang Sun,Dong-Ki Kim,Jonathan P. How
In a multirobot system, a number of cyber-physical attacks (e.g., communication hijack, observation per-turbations) can challenge the robustness of agents. This robust-ness 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 thi...
