7 papers
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele +2
Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data effic…
Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow +1
Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly…
Kernel conditional tests from learning-theoretic bounds
Pierre-François Massiani, Christian Fiedler, Lukas Haverbeck +2
We propose a framework for hypothesis testing on conditional probability distributions, which we then use to construct statistical tests of functionals of conditional distributions…
Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF
Tobin Holtmann, David Stenger, Andres Posada-Moreno +2
State estimation in control and systems engineering traditionally requires extensive manual system identification or data-collection effort. However, transformer-based foundation m…
On Rollouts in Model-Based Reinforcement Learning
Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow +1
Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated mo…
Event-Triggered Time-Varying Bayesian Optimization
Paul Brunzema, Alexander von Rohr, Friedrich Solowjow +1
We consider the problem of sequentially optimizing a time-varying objective function using time-varying Bayesian optimization (TVBO). Current approaches to TVBO require prior knowl…