Deep-attack over the deep reinforcement learning

• Main Authors: Li, Yang, Pan, Quan, Cambria, Erik
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Adversarial Attack; Deep Reinforcement Learning
• Online Access: https://hdl.handle.net/10356/162724
• Institution: Nanyang Technological University

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design an attack evaluation function to select critical points that...