Interpretable policies for reinforcement learning by genetic programming von Hein, Daniel, Udluft, Steffen, Runkler, Thomas A.

Volltext

Particle swarm optimization for generating interpretable fuzzy reinforcement learning policies von Hein, Daniel, Hentschel, Alexander, Runkler, Thomas, Udluft, Steffen

Volltext

Overcoming model bias for robust offline deep reinforcement learning von Swazinna, Phillip, Udluft, Steffen, Runkler, Thomas

Volltext

Exploiting similarity in system identification tasks with recurrent neural networks von Spieckermann, Sigurd, Düll, Siegmund, Udluft, Steffen, Hentschel, Alexander, Runkler, Thomas

Volltext

Safe Policy Improvement Approaches and Their Limitations von Scholl, Philipp, Dietrich, Felix, Otte, Clemens, Udluft, Steffen

Volltext

Reinforcement Learning with Particle Swarm Optimization Policy (PSO-P) in Continuous State and Action Spaces von Hein, Daniel, Hentschel, Alexander, Runkler, Thomas A, Udluft, Steffen

Volltext

Neural-ANOVA: Model Decomposition for Interpretable Machine Learning von Limmer, Steffen, Udluft, Steffen, Otte, Clemens

Volltext bestellen

Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data von Hans, Alexander, Udluft, Steffen

Volltext

Learning long-term dependencies with recurrent neural networks von Schaefer, Anton Maximilian, Udluft, Steffen, Zimmermann, Hans-Georg

Volltext

Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning von Swazinna, Phillip, Udluft, Steffen, Hein, Daniel, Runkler, Thomas

Volltext

Method and device for predicting the time remaining of a signal phase von Depeweg, Stefan, Udluft, Steffen

Volltext bestellen

Automatic Trade-off Adaptation in Offline RL von Swazinna, Phillip, Udluft, Steffen, Runkler, Thomas

Volltext bestellen

TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning von Ormancı, Batıkan Bora, Swazinna, Phillip, Udluft, Steffen, Runkler, Thomas A

Volltext bestellen

MACHINE CONTROL AND METHOD FOR CONFIGURING THE MACHINE CONTROL von Hein, Daniel, Udluft, Steffen

Volltext bestellen

METHOD AND CONTROL DEVICE FOR CONTROLLING A MACHINE von Swazinna, Phillip, Udluft, Steffen

Volltext bestellen

Why long model-based rollouts are no reason for bad Q-value estimates von Wissmann, Philipp, Hein, Daniel, Udluft, Steffen, Tresp, Volker

Volltext bestellen

Model-based Offline Quantum Reinforcement Learning von Eisenmann, Simon, Hein, Daniel, Udluft, Steffen, Runkler, Thomas A

Volltext bestellen

User-Interactive Offline Reinforcement Learning von Swazinna, Phillip, Udluft, Steffen, Runkler, Thomas

Volltext bestellen

METHOD AND DEVICE FOR PREDICTING THE TIME REMAINING OF A SIGNAL PHASE von Depeweg, Stefan, Udluft, Steffen

Volltext bestellen

METHOD AND DEVICE FOR PREDICTING THE TIME REMAINING OF A SIGNAL PHASE von UDLUFT, Steffen, DEPEWEG, Stefan

Volltext bestellen