f0eb6568ea114ba6e293f903c34d7488-Paper.pdf

Several works haveshown this vulnerability via adversarial attacks, butexisting approaches onimproving therobustness ofDRL under this setting have limited success and lack for theoretical principles. We show that naively applying existing techniques on improving robustness for classification tasks,likeadversarialtraining,areineffectiveformanyRLtasks.