2 citations · 3 across the 8 of their papers we have counts for
8 papers
Gray-Box Optimization using Optimism in the Face of Uncertainty
Katrin Baumgärtner, Léo Simpson, Moritz Diehl
This paper considers sequential gray-box optimization where the objective function is given as the composition of a loss function and a parametric model. Crucially, the parameters…
Anderson Acceleration for Linearly Converging SQP-Type Methods
Jonathan Frey, David Kiessling, Katrin Baumgärtner +1
Although Anderson acceleration (AA) is known to speed up fixed-point iterations, it is rarely applied in constrained optimization, in particular sequential quadratic programming (S…
Finite-sample bounds for multi-output system identification
Léo Simpson, Katrin Baumgärtner, Johannes Köhler +1
This paper presents uniform-in-time error bounds for regularized linear regression with vector-valued outputs and conditionally zero-mean subgaussian noise. By revisitileveraging s…
A Comparative Study of MINLP and MPVC Formulations for Solving Complex Nonlinear Decision-Making Problems in Aerospace Applications
Andrea Ghezzi, Armin Nurkanović, Avishai Weiss +2
High-level decision-making for dynamical systems often involves performance and safety specifications that are activated or deactivated depending on conditions related to the syste…
Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control
Andrea Ghezzi, Rudolf Reiter, Katrin Baumgärtner +2
We propose a computationally efficient rollout-then-optimize method to improve a learned control policy at deployment time. A learned policy provides a nominal trajectory, which is…
Bayesian Optimization with Lower Confidence Bounds for Minimization Problems with Known Outer Structure
Katrin Baumgärtner, Moritz Diehl
This paper considers Bayesian optimization (BO) for problems with known outer problem structure. In contrast to the classic BO setting, where the objective function itself is unkno…
Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification
Rudolf Reiter, Jasper Hoffmann, Dirk Reinhardt +6
The fields of MPC and RL consider two successful control techniques for Markov decision processes. Both approaches are derived from similar fundamental principles, and both are wid…
AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control
Rudolf Reiter, Andrea Ghezzi, Katrin Baumgärtner +3
\Ac{MPC} and \ac{RL} are two powerful control strategies with, arguably, complementary advantages. In this work, we show how actor-critic \ac{RL} techniques can be leveraged to imp…