Imitation learning of stabilizing policies for nonlinear systems

DOI10.1016/j.ejcon.2022.100678zbMath1501.93107arXiv2109.10854OpenAlexW3199389974MaRDI QIDQ2095315

Sebastian East

Publication date: 9 November 2022

Published in: European Journal of Control (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.10854

zbMATH Keywords

nonlinear systemsLyapunov functionsgradient descentalternating direction method of multipliersimitation learningsum of squares optimization

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05) Synthesis problems (93B50)

Uses Software

• SymPy
• CVXPY
• SCS
• GitHub
• JAX

Cites Work

• CVXPY: A Python-Embedded Modeling Language for Convex Optimization
• ADMM for multiaffine constrained optimization
• The explicit linear quadratic regulator for constrained systems

This page was built for publication: Imitation learning of stabilizing policies for nonlinear systems