5 papers
PAC-Bayesian Certificates for Quadratic Closed-Loop Control
Domagoj Herceg
PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objectiv…
Distributionally Robust PAC-Bayesian Control
Domagoj Herceg, Duarte Antunes
We present a distributionally robust PAC-Bayesian framework for certifying the performance of learning-based finite-horizon controllers. While existing PAC-Bayes control literature…
Tempering the Bayes Filter towards Improved Model-Based Estimation
Menno van Zutphen, Domagoj Herceg, Giannis Delimpaltadakis +1
Model-based filtering is often carried out while subject to an imperfect model, as learning partially-observable stochastic systems remains a challenge. Recent work on Bayesian inf…
A Scenario-based Model Predictive Control Scheme for Pandemic Response through Non-pharmaceutical Interventions
Domagoj Herceg, Marco DellOro, Riccardo Bertollo +5
This paper presents a scenario-based model predictive control (MPC) scheme designed to control an evolving pandemic via non-pharmaceutical intervention (NPIs). The proposed approac…
Beyond KL-divergence: Risk Aware Control Through Cross Entropy and Adversarial Entropy Regularization
Menno van Zutphen, Domagoj Herceg, Duarte J. Antunes
While the idea of robust dynamic programming (DP) is compelling for systems affected by uncertainty, addressing worst-case disturbances generally results in excessive conservatism.…