Learning key steps to attack deep reinforcement learning agents

DOI10.1007/S10994-023-06318-9MaRDI QIDQ6161208zbMATH OpenOpenAlexFDO

Authors Chien-Min Yu, Ming-Hsin Chen, Hsuan-Tien Lin

Publication date 27 June 2023

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-023-06318-9

zbMATH Keywords

adversarial attacksdeep learningreinforcement learningrobustness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals
• Deep reinforcement learning control approach to mitigating actuator attacks
• Online inverse reinforcement learning for nonlinear systems with adversarial attacks
• Theoretical investigation of generalization bounds for adversarial learning of deep neural networks
• Learning reward machines: a study in partially observable reinforcement learning

Cites work

• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• End-to-end training of deep visuomotor policies
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 7626725 (Why is no real title available?)
• Reinforcement learning. An introduction
• Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

Cited in

(1)

• Deep reinforcement learning control approach to mitigating actuator attacks

This page was built for publication: Learning key steps to attack deep reinforcement learning agents

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6161208)