79 citations · 139 across the 6 of their papers we have counts for
5 papers · 1 filter
Interpretable reinforcement learning with decision-tree pruning
Mark Leon Ringer, Michel Tokic
Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness. Converting a trained policy into explicit decision-tree rules…
TSFM in-context learning for time-series classification of bearing-health status
Michel Tokic, Slobodan Djukanović, Anja von Beuningen +1
We introduce a classification method based on in-context learning using time-series foundation models (TSFMs). We demonstrate how data not included in the TSFM training can be clas…
Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics
Manuel A. Roehrl, Thomas A. Runkler, Veronika Brandtstetter +2
Identifying accurate dynamic models is required for the simulation and control of various technical systems. In many important real-world applications, however, the two main modeli…
Batch Reinforcement Learning on the Industrial Benchmark: First Experiences
Daniel Hein, Steffen Udluft, Michel Tokic +3
The Particle Swarm Optimization Policy (PSO-P) has been recently introduced and proven to produce remarkable results on interacting with academic reinforcement learning benchmarks…
Introduction to the "Industrial Benchmark"
Daniel Hein, Alexander Hentschel, Volkmar Sterzing +2
A novel reinforcement learning benchmark, called Industrial Benchmark, is introduced. The Industrial Benchmark aims at being be realistic in the sense, that it includes a variety o…