Reward Certification for Policy Smoothed Reinforcement Learning

R Mu, LS Marcolino, Y Zhang, T Zhang… - Proceedings of the …, 2024 - ojs.aaai.org
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it
can be weakened by adversarial attacks. Recent studies have introduced``smoothed …
被引用次数：1 相关文章

Reward Certification for Policy Smoothed Reinforcement Learning

R Mu, L Soriano Marcolino, T Zhang, Y Zhang… - arXiv e …, 2023 - ui.adsabs.harvard.edu
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it
can be weakened by adversarial attacks. Recent studies have introduced" smoothed …

Reward Certification for Policy Smoothed Reinforcement Learning

R Mu, LS Marcolino, T Zhang, Y Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it
can be weakened by adversarial attacks. Recent studies have introduced" smoothed …