Lessons from AlphaZero for optimal, model predictive, and adaptive control

MaRDI QIDQ6600658zbMATH OpenFDO

Authors Dimitri P. Bertsekas

Publication date 9 September 2024

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to operations research and mathematical programming (90-02) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Research exposition (monographs, survey articles) pertaining to systems and control theory (93-02) Model predictive control (93B45) Adaptive control/observation systems (93C40)

Recommendations

• Dynamic programming and optimal control. Vol. 1.
• Optimal adaptive control and differential games by reinforcement learning principles
• Adaptive dynamic programming for control. Algorithms and stability
• Reinforcement Learning for Sequential Decision and Optimal Control
• Adaptive dynamic programming for an online solution of a zero-sum differential game

Cited in

(3)

• Deep networks for system identification: a survey
• Engineering game theory: mathematical principles and applications in power systems
• Dimitri P. Bertsekas (1942--2026): in memoriam

This page was built for publication: Lessons from AlphaZero for optimal, model predictive, and adaptive control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6600658)