Nash-regularized control policy learning of linear-quadratic zero-sum differential games from demonstrations

DOI10.1137/1.9781611977745.7zbMATH Open1545.9101MaRDI QIDQ6567642FDOQ6567642

Authors: Courtney M. King, Juntao Chen 

Publication date: 5 July 2024

Recommendations

• Non-zero sum Nash Q-learning for unknown deterministic continuous-time linear systems
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games
• Inverse reinforcement learning for identification of linear-quadratic zero-sum differential games
• Reinforcement learning and non-zero-sum game output regulation for multi-player linear uncertain systems

Mathematics Subject Classification ID

Differential games and control (49N70) Noncooperative games (91A10) Differential games (aspects of game theory) (91A23) 2-person games (91A05)

This page was built for publication: Nash-regularized control policy learning of linear-quadratic zero-sum differential games from demonstrations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6567642)