Robust convergence of the steepest descent method for data-based control

DOI10.1080/00207721.2011.563874zbMath1305.93143OpenAlexW1973212500MaRDI QIDQ2935099

Alexandre Sanfelice Bazanella, Diego Eckhard

Publication date: 22 December 2014

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207721.2011.563874

zbMATH Keywords

stochastic approximationnonlinear programmingrobust estimationdiscrete time systems

Mathematics Subject Classification ID

Nonlinear programming (90C30) Control/observation systems involving computers (process control, etc.) (93C83) Discrete-time control/observation systems (93C55) Linear systems in control theory (93C05)

Related Items (3)

Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning ⋮ Cost function shaping of the output error criterion ⋮ Gradient Descent Learns Linear Dynamical Systems

Cites Work

• Iterative minimization of \(H_2\) control performance criteria
• Iterative feedback tuning—an overview
• Model reference adaptive control of the output stochastic distributions for unknown linear stochastic systems
• Iterative correlation‐based controller tuning
• Direct iterative tuning via spectral analysis

This page was built for publication: Robust convergence of the steepest descent method for data-based control