ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning

While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness, particularly against adversarial perturbations, remains unexplored. Unfortunately, the attacks and robust representation training methods specifically designed for traditional RL are not so effective when applied to GCRL. To address this challenge, we propose the \textit{Semi-Contrastive Representation} attack, a novel approach inspired by the adversarial contrastive attack. Unlike existing attacks in RL, it only necessitates information from the policy function and can be seamlessly implemented during deployment. Furthermore, to mitigate the vulnerability of existing GCRL algorithms, we introduce \textit{Adversarial Representation Tactics}. This strategy combines \textit{Semi-Contrastive Adversarial Augmentation} with \textit{Sensitivity-Aware Regularizer}. It improves the adversarial robustness of the underlying agent against various types of perturbations. Extensive experiments validate the superior performance of our attack and defence mechanism across multiple state-of-the-art GCRL algorithms. Our tool {\bf ReRoGCRL} is available at \url{https://github.com/TrustAI/ReRoGCRL}.