2 papers
math.OC2025
Reinforcement learning for adaptive interior point methods in convex quadratic programming
Jeremy Bertoncini, Alberto De Marchi, Matthias Gerdts +1
Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumption…
math.OC2024
Reinforcement Learning for Docking Maneuvers with Prescribed Performance
Simon Gottschalk, Lukas Lanza, Karl Worthmann +1
We propose a two-component data-driven controller to safely perform docking maneuvers for satellites. Reinforcement Learning is used to deduce an optimal control policy based on me…