Deep-attack over the deep reinforcement learning
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...
Saved in:
Main Authors: | Li, Yang, Pan, Quan, Cambria, Erik |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Article |
語言: | English |
出版: |
2022
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/162724 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Minimalistic attacks : how little it takes to fool deep reinforcement learning policies
由: Qu, Xinghua, et al.
出版: (2021) -
Robust data-driven adversarial false data injection attack detection method with deep Q-network in power systems
由: Ran, Xiaohong, et al.
出版: (2024) -
Goal modelling for deep reinforcement learning agents
由: Leung, Jonathan, et al.
出版: (2022) -
Challenges and countermeasures for adversarial attacks on deep reinforcement learning
由: Ilahi, Inaam, et al.
出版: (2022) -
Towards characterizing adversarial defects of deep learning software from the lens of uncertainty
由: ZHANG, Xiyue, et al.
出版: (2020)