Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals

DOI10.1007/978-3-030-32430-8_14zbMath1440.68215arXiv1906.10571OpenAlexW2981396729MaRDI QIDQ3297666

Quanyan Zhu, Yunhan Huang

Publication date: 20 July 2020

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.10571

zbMATH Keywords

reinforcement learningQ-learningdeceptioncybersecurityadversarial learningcounterdeception

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Control/observation systems involving computers (process control, etc.) (93C83) Computer security (68M25)

Related Items

Unnamed Item

Uses Software

• CVX
• Mosek

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• \({\mathcal Q}\)-learning
• On theorems of the alternative
• Game-Theoretic Approach to Feedback-Driven Multi-stage Moving Target Defense
• Game-Theoretic Methods for Robustness, Security, and Resilience of Cyberphysical Control Systems: Games-in-Games Principle for Optimal Cross-Layer Resilient Control Systems
• Deceptive Routing in Relay Networks
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning