论文标题
一项有关加强学习安全性的调查，并应用于自动驾驶
A Survey on Reinforcement Learning Security with Application to Autonomous Driving
论文作者
论文摘要
强化学习使机器可以从自己的经验中学习。如今，尽管容易受到精心制作的攻击，以防止强化学习算法了解有效可靠的政策，或者诱使受过训练的代理商做出错误的决定，但它被用于安全至关重要的应用程序，例如自主驾驶。有关增强学习安全性的文献正在迅速增长，并提出了一些调查以阐明这一领域。但是，鉴于手头的系统类型，它们的分类不足以选择适当的防御。在我们的调查中，我们不仅通过考虑不同的观点来克服这一限制，而且还讨论了在自主驾驶中使用强化学习算法时最新攻击和防御措施的适用性。
Reinforcement learning allows machines to learn from their own experience. Nowadays, it is used in safety-critical applications, such as autonomous driving, despite being vulnerable to attacks carefully crafted to either prevent that the reinforcement learning algorithm learns an effective and reliable policy, or to induce the trained agent to make a wrong decision. The literature about the security of reinforcement learning is rapidly growing, and some surveys have been proposed to shed light on this field. However, their categorizations are insufficient for choosing an appropriate defense given the kind of system at hand. In our survey, we do not only overcome this limitation by considering a different perspective, but we also discuss the applicability of state-of-the-art attacks and defenses when reinforcement learning algorithms are used in the context of autonomous driving.
