A survey on reinforcement learning security with application to autonomous driving

[PDF] ieee.org

Performance improvement on traditional Chinese task-oriented dialogue systems with reinforcement learning and regularized dropout technique

JS Sheu, SR Wu, WH Wu - IEEE Access, 2023 - ieeexplore.ieee.org
The development of conversational voice assistant applications has been in full swing
around the world. This paper aims to develop traditional Chinese multi-domain task-oriented …
被引用次数：4 相关文章 所有 2 个版本
[PDF] arxiv.org

Adaptive Discounting of Training Time Attacks

R Bector, A Aradhya, C Quek, Z Rabinovich - arXiv preprint arXiv …, 2024 - arxiv.org
Among the most insidious attacks on Reinforcement Learning (RL) solutions are training-
time attacks (TTAs) that create loopholes and backdoors in the learned behaviour. Not …
相关文章 所有 4 个版本
[PDF] unica.it

Detecting Attacks Against Deep Reinforcement Learning for Autonomous Driving

M Pintor, L Demetrio, A Sotgiu, HY Lin… - 2023 International …, 2023 - ieeexplore.ieee.org
With the advent of deep reinforcement learning, we witness the spread of novel autonomous
driving agents that learn how to drive safely among humans. However, skilled attackers …
相关文章 所有 4 个版本