Q-learning for linear closed-loop Stackelberg strategy with one-step memory

DOI10.1016/J.JFRANKLIN.2025.108151MaRDI QIDQ6841750zbMATH OpenFDO

Authors Hongdan Li, Juanjuan Xu, Huanshui Zhang

Publication date 20 March 2026

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JFRANKLIN.2025.108151

zbMATH Keywords

Q-learningone-step memorylinear closed-loop Stackelberg strategy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Linear-quadratic optimal control problems (49N10) Hierarchical games (including Stackelberg games) (91A65) Discrete-time games (91A50)

Cites work

• scientific article; zbMATH DE number 3634142 (Why is no real title available?)
• scientific article; zbMATH DE number 1243371 (Why is no real title available?)
• scientific article; zbMATH DE number 1734466 (Why is no real title available?)
• scientific article; zbMATH DE number 836596 (Why is no real title available?)
• Closed-loop Stackelberg strategies with applications in the optimal control of multilevel systems
• Controllability of stochastic game-based control systems
• Equilibrium points in n -person games
• Necessary and Sufficient Condition for Two-Player Stackelberg Strategy
• Nonclassical control problems and Stackelberg games
• Open-loop Stackelberg learning solution for hierarchical control problems
• Stackelberg strategies for stochastic systems with multiple followers
• Stackelburg solution for two-person games with biased information patterns
• The maximum principle for global solutions of stochastic Stackelberg differential games

This page was built for publication: Q-learning for linear closed-loop Stackelberg strategy with one-step memory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6841750)