Steffen Udluft

Publication Activity (10 Years)

Years Active: 2006-2024
Publications (10 Years): 40

Top Topics

Markov Decision Process

Policy Iteration

Reinforcement Learning

Genetic Programming

Top Venues

Eng. Appl. Artif. Intell.

Publications

Simon Eisenmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler
Model-based Offline Quantum Reinforcement Learning. CoRR (2024)
Philipp Wissmann, Daniel Hein, Steffen Udluft, Volker Tresp
Why long model-based rollouts are no reason for bad Q-value estimates. CoRR (2024)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Automatic Trade-off Adaptation in Offline RL. CoRR (2023)
Simon Wiedemann, Daniel Hein, Steffen Udluft, Christian B. Mendl
Quantum Policy Iteration via Amplitude Estimation and Grover Search - Towards Quantum Advantage for Reinforcement Learning. Trans. Mach. Learn. Res. 2023 (2023)
Marc Weber, Phillip Swazinna, Daniel Hein, Steffen Udluft, Volkmar Sterzing
Learning Control Policies for Variable Objectives from Offline Data. SSCI (2023)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
User-Interactive Offline Reinforcement Learning. ICLR (2023)
Marc Weber, Phillip Swazinna, Daniel Hein, Steffen Udluft, Volkmar Sterzing
Learning Control Policies for Variable Objectives from Offline Data. CoRR (2023)
Volker Tresp, Steffen Udluft, Daniel Hein, Werner Hauptmann, Martin Leib, Christopher Mutschler, Daniel D. Scherer, Wolfgang Mauerer
Workshop Summary: Quantum Machine Learning. QCE (2023)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Automatic Trade-off Adaptation in Offline RL. ESANN (2023)
Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
Safe Policy Improvement Approaches and Their Limitations. ICAART (Revised Selected Paper (2022)
Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
Safe Policy Improvement Approaches and their Limitations. CoRR (2022)
Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning. CoRR (2022)
Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
Safe Policy Improvement Approaches on Discrete Markov Decision Processes. ICAART (2) (2022)
Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
Safe Policy Improvement Approaches on Discrete Markov Decision Processes. CoRR (2022)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
User-Interactive Offline Reinforcement Learning. CoRR (2022)
Simon Wiedemann, Daniel Hein, Steffen Udluft, Christian Mendl
Quantum Policy Iteration via Amplitude Estimation and Grover Search - Towards Quantum Advantage for Reinforcement Learning. CoRR (2022)
Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
Behavior Constraining in Weight Space for Offline Reinforcement Learning. ESANN (2021)
Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
Behavior Constraining in Weight Space for Offline Reinforcement Learning. CoRR (2021)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Overcoming model bias for robust offline deep reinforcement learning. Eng. Appl. Artif. Intell. 104 (2021)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning. SSCI (2021)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning. CoRR (2021)
Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
Overcoming Model Bias for Robust Offline Deep Reinforcement Learning. CoRR (2020)
Daniel Hein, Steffen Udluft, Thomas A. Runkler
Generating interpretable reinforcement learning policies using genetic programming. GECCO (Companion) (2019)
Daniel Hein, Steffen Udluft, Thomas A. Runkler
Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming. CoRR (2018)
Daniel Hein, Steffen Udluft, Thomas A. Runkler
Interpretable policies for reinforcement learning by genetic programming. Eng. Appl. Artif. Intell. 76 (2018)
Stefan Depeweg, José Miguel Hernández-Lobato, Steffen Udluft, Thomas A. Runkler
Sensitivity analysis for predictive uncertainty. ESANN (2018)
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. ICML (2018)
Daniel Hein, Steffen Udluft, Thomas A. Runkler
Generating interpretable fuzzy controllers using particle swarm optimization and genetic programming. GECCO (Companion) (2018)
Daniel Hein, Steffen Udluft, Thomas A. Runkler
Interpretable Policies for Reinforcement Learning by Genetic Programming. CoRR (2017)
Daniel Hein, Steffen Udluft, Michel Tokic, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
Batch Reinforcement Learning on the Industrial Benchmark: First Experiences. CoRR (2017)
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems. CoRR (2017)
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. ICLR (Poster) (2017)
Daniel Hein, Steffen Udluft, Michel Tokic, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
Batch reinforcement learning on the industrial benchmark: First experiences. IJCNN (2017)
Daniel Hein, Stefan Depeweg, Michel Tokic, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
A Benchmark Environment Motivated by Industrial Control Problems. CoRR (2017)
Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
Particle swarm optimization for generating interpretable fuzzy reinforcement learning policies. Eng. Appl. Artif. Intell. 65 (2017)
Daniel Hein, Stefan Depeweg, Michel Tokic, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
A benchmark environment motivated by industrial control problems. SSCI (2017)
Daniel Hein, Alexander Hentschel, Volkmar Sterzing, Michel Tokic, Steffen Udluft
Introduction to the "Industrial Benchmark". CoRR (2016)
Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
Reinforcement Learning with Particle Swarm Optimization Policy (PSO-P) in Continuous State and Action Spaces. Int. J. Swarm Intell. Res. 7 (3) (2016)
Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
Particle Swarm Optimization for Generating Fuzzy Reinforcement Learning Policies. CoRR (2016)
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. CoRR (2016)
Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler
Exploiting similarity in system identification tasks with recurrent neural networks. Neurocomputing 169 (2015)
Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler
Exploiting similarity in system identification tasks with recurrent neural networks. ESANN (2014)
Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Thomas A. Runkler
Regularized Recurrent Neural Networks for Data Efficient Dual-Task Learning. ICANN (2014)
Siegmund Duell, Steffen Udluft
Ensembles for Continuous Actions in Reinforcement Learning. ESANN (2013)
Siegmund Duell, Lina Weichbrodt, Alexander Hans, Steffen Udluft
Recurrent Neural State Estimation in Domains with Long-Term Dependencies. ESANN (2012)
Thomas A. Runkler, Steffen Udluft, Siegmund Düll
Datenbasierte Optimalsteuerung mit neuronalen Netzen und dateneffizientem Reinforcement Learning. Autom. 60 (10) (2012)
Alexander Hans, Steffen Udluft
Ensemble Usage for More Reliable Policy Identification in Reinforcement Learning. ESANN (2011)
Alexander Hans, Siegmund Duell, Steffen Udluft
Agent self-assessment: Determining policy quality without execution. ADPRL (2011)
Alexander Hans, Steffen Udluft
Uncertainty Propagation for Efficient Exploration in Reinforcement Learning. ECAI (2010)
Siegmund Duell, Alexander Hans, Steffen Udluft
The Markov Decision Process Extraction Network. ESANN (2010)
Alexander Hans, Steffen Udluft
Ensembles of Neural Networks for Robust Reinforcement Learning. ICMLA (2010)
Volkmar Sterzing, Steffen Udluft
Dateneffizientes Reinforcement-Learning. Künstliche Intell. 23 (3) (2009)
Alexander Hans, Steffen Udluft
Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data. ICANN (1) (2009)
Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann
Learning long-term dependencies with recurrent neural networks. Neurocomputing 71 (13-15) (2008)
Alexander Hans, Daniel Schneegaß, Anton Maximilian Schäfer, Steffen Udluft
Safe exploration for reinforcement learning. ESANN (2008)
Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
Uncertainty propagation for quality assurance in Reinforcement Learning. IJCNN (2008)
Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
Explicit Kernel Rewards Regression for data-efficient near-optimal policy identification. ESANN (2007)
Anton Maximilian Schäfer, Daniel Schneegaß, Volkmar Sterzing, Steffen Udluft
A Neural Reinforcement Learning Approach to Gas Turbine Control. IJCNN (2007)
Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
Neural Rewards Regression for near-optimal policy identification in Markovian and partial observable environments. ESANN (2007)
Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification. ICANN (1) (2007)
Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann
The Recurrent Control Neural Network. ESANN (2007)
Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
Kernel Rewards Regression: An Information Efficient Batch Policy Iteration Approach. Artificial Intelligence and Applications (2006)
Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann
Learning Long Term Dependencies with Recurrent Neural Networks. ICANN (1) (2006)