Logarithmic regret in online linear quadratic control using Riccati updates

DOI10.1007/s00498-022-00323-4zbMath1498.49054OpenAlexW4226099433MaRDI QIDQ2674833

Yanyan Li

Publication date: 14 September 2022

Published in: MCSS. Mathematics of Control, Signals, and Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00498-022-00323-4

zbMATH Keywords

Riccati equationonline optimal controllogarithmic regretNewton-Hewer Riccati updateonline linear quadratic control

Mathematics Subject Classification ID

Semidefinite programming (90C22) Linear-quadratic optimal control problems (49N10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Logarithmic regret algorithms for online convex optimization
• Model predictive control: Theory and practice - a survey
• A data-driven approach to robust control of multivariable systems by convex optimization
• Discrete-time stochastic systems. Estimation and control.
• On the lack of monotonicity of Newton-Hewer updates for Riccati equations
• An optimal algorithm for stochastic strongly-convex optimization
• Stable Optimal Control and Semicontractive Dynamic Programming
• Online Learning and Online Convex Optimization
• Semidefinite programming duality and linear time-invariant systems
• Prediction, Learning, and Games
• On the discrete time matrix Riccati equation of optimal control†

This page was built for publication: Logarithmic regret in online linear quadratic control using Riccati updates