تقرير
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
| العنوان: | ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning |
|---|---|
| المؤلفون: | Yin, Xiangyu, Wu, Sihao, Liu, Jiaxu, Fang, Meng, Zhao, Xingyu, Huang, Xiaowei, Ruan, Wenjie |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| الوصف: | While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness against adversarial perturbations remains unexplored. The attacks and robust representation training methods that are designed for traditional RL become less effective when applied to GCRL. To address this challenge, we first propose the 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. Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations. Extensive experiments validate the superior performance of our attack and defence methods across multiple state-of-the-art GCRL algorithms. Our tool ReRoGCRL is available at https://github.com/TrustAI/ReRoGCRL. Comment: This paper has been accepted in AAAI24 (https://aaai.org/aaai-conference/) |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2312.07392 |
| رقم الأكسشن: | edsarx.2312.07392 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |