تقرير
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
العنوان: | Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey |
---|---|
المؤلفون: | Schott, Lucas, Delas, Josephine, Hajri, Hatem, Gherbi, Elies, Yaich, Reda, Boulahia-Cuppens, Nora, Cuppens, Frederic, Lamprier, Sylvain |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
الوصف: | Deep Reinforcement Learning (DRL) is an approach for training autonomous agents across various complex environments. Despite its significant performance in well known environments, it remains susceptible to minor conditions variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve robustness of DRL to unknown changes in the conditions is through Adversarial Training, by training the agent against well suited adversarial attacks on the dynamics of the environment. Addressing this critical issue, our work presents an in-depth analysis of contemporary adversarial attack methodologies, systematically categorizing them and comparing their objectives and operational mechanisms. This classification offers a detailed insight into how adversarial attacks effectively act for evaluating the resilience of DRL agents, thereby paving the way for enhancing their robustness. Comment: 57 pages, 16 figues, 2 tables |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2403.00420 |
رقم الأكسشن: | edsarx.2403.00420 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |