Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910738397790208 |
|---|---|
| author | Schott, Lucas Delas, Josephine Hajri, Hatem Gherbi, Elies Yaich, Reda Boulahia-Cuppens, Nora Cuppens, Frederic Lamprier, Sylvain |
| author_facet | Schott, Lucas Delas, Josephine Hajri, Hatem Gherbi, Elies Yaich, Reda Boulahia-Cuppens, Nora Cuppens, Frederic Lamprier, Sylvain |
| contents | Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against well-suited adversarial attacks on the observations and the dynamics of the environment. Addressing this critical issue, our work presents an in-depth analysis of contemporary adversarial attack and training methodologies, systematically categorizing them and comparing their objectives and operational mechanisms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00420 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey Schott, Lucas Delas, Josephine Hajri, Hatem Gherbi, Elies Yaich, Reda Boulahia-Cuppens, Nora Cuppens, Frederic Lamprier, Sylvain Machine Learning Artificial Intelligence Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against well-suited adversarial attacks on the observations and the dynamics of the environment. Addressing this critical issue, our work presents an in-depth analysis of contemporary adversarial attack and training methodologies, systematically categorizing them and comparing their objectives and operational mechanisms. |
| title | Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.00420 |