| 2026 | ESANN | Point-wise Q-value maximization for converging Q-learning in continuous state-spaces. | Philipp Wissmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2026 | ESANN | Efficient and Resilient Machine Learning for Industrial Applications. | Philipp Wissmann, Philip Naumann, Daniel Hein, Steffen Udluft, Marc Weber, Simon Leszek, Thomas A. Runkler |
| 2025 | ESANN | TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning. | Batikan Bora Ormanci, Phillip Swazinna, Steffen Udluft, Thomas A. Runkler |
| 2025 | ESANN | Is Q-learning an Ill-posed Problem? | Philipp Wissmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2025 | QCE | From Classical Data to Quantum Advantage - Quantum Policy Evaluation on Quantum Hardware. | Daniel Hein, Simon Wiedemann, Markus Baumann, Patrik Felbinger, Justin Klein, Maximilian Schieder, Jonas Stein, Danille Schuman, Thomas Cope, Steffen Udluft |
| 2025 | QCE | Variational Quantum Circuits in Offline Contextual Bandit Problems. | Lukas Schulte, Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2025 | QCE | First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies. | Yize Sun, Mohamad Hagog, Marc Weber, Daniel Hein, Steffen Udluft, Yunpu Ma, Volker Tresp |
| 2025 | QCE | Learning Control with Simulated Variational Quantum Policies in a Surrogate Cart-Pole Environment. | Yize Sun, Mohamad Hagog, Marc Weber, Daniel Hein, Steffen Udluft, Yunpu Ma, Volker Tresp |
| 2024 | ESANN | Why long model-based rollouts are no reason for bad Q-value estimates. | Philipp Wissmann, Daniel Hein, Steffen Udluft, Volker Tresp |
| 2024 | QCE | Model-Based Offline Quantum Reinforcement Learning. | Simon Eisenmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2023 | ESANN | Automatic Trade-off Adaptation in Offline RL. | Phillip Swazinna, Steffen Udluft, Thomas A. Runkler |
| 2023 | ICLR | User-Interactive Offline Reinforcement Learning. | Phillip Swazinna, Steffen Udluft, Thomas A. Runkler |
| 2023 | QCE | Workshop Summary: Quantum Machine Learning. | Volker Tresp, Steffen Udluft, Daniel Hein, Werner Hauptmann, Martin Leib, Christopher Mutschler, Daniel D. Scherer, Wolfgang Mauerer |
| 2022 | ICAART | Safe Policy Improvement Approaches on Discrete Markov Decision Processes. | Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft |
| 2022 | ICAART | Safe Policy Improvement Approaches and Their Limitations. | Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft |
| 2021 | ESANN | Behavior Constraining in Weight Space for Offline Reinforcement Learning. | Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler |
| 2019 | GECCO | Generating interpretable reinforcement learning policies using genetic programming. | Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2018 | ESANN | Sensitivity analysis for predictive uncertainty. | Stefan Depeweg, Jos Miguel Hernndez-Lobato, Steffen Udluft, Thomas A. Runkler |
| 2018 | GECCO | Generating interpretable fuzzy controllers using particle swarm optimization and genetic programming. | Daniel Hein, Steffen Udluft, Thomas A. Runkler |
| 2018 | ICML | Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. | Stefan Depeweg, Jos Miguel Hernndez-Lobato, Finale Doshi-Velez, Steffen Udluft |
| 2017 | ICLR | Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. | Stefan Depeweg, Jos Miguel Hernndez-Lobato, Finale Doshi-Velez, Steffen Udluft |
| 2017 | IJCNN | Batch reinforcement learning on the industrial benchmark: First experiences. | Daniel Hein, Steffen Udluft, Michel Tokic, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing |
| 2014 | ESANN | Exploiting similarity in system identification tasks with recurrent neural networks. | Sigurd Spieckermann, Siegmund Dll, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler |
| 2014 | ICANN | Regularized Recurrent Neural Networks for Data Efficient Dual-Task Learning. | Sigurd Spieckermann, Siegmund Dll, Steffen Udluft, Thomas A. Runkler |
| 2013 | ESANN | Ensembles for Continuous Actions in Reinforcement Learning. | Siegmund Duell, Steffen Udluft |
| 2012 | ESANN | Recurrent Neural State Estimation in Domains with Long-Term Dependencies. | Siegmund Duell, Lina Weichbrodt, Alexander Hans, Steffen Udluft |
| 2011 | ESANN | Ensemble Usage for More Reliable Policy Identification in Reinforcement Learning. | Alexander Hans, Steffen Udluft |
| 2010 | ECAI | Uncertainty Propagation for Efficient Exploration in Reinforcement Learning. | Alexander Hans, Steffen Udluft |
| 2010 | ESANN | The Markov Decision Process Extraction Network. | Siegmund Duell, Alexander Hans, Steffen Udluft |
| 2010 | ICMLA | Ensembles of Neural Networks for Robust Reinforcement Learning. | Alexander Hans, Steffen Udluft |
| 2009 | ICANN | Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data. | Alexander Hans, Steffen Udluft |
| 2008 | ESANN | Safe exploration for reinforcement learning. | Alexander Hans, Daniel Schneega, Anton Maximilian Schfer, Steffen Udluft |
| 2008 | IJCNN | Uncertainty propagation for quality assurance in Reinforcement Learning. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ESANN | The Recurrent Control Neural Network. | Anton Maximilian Schfer, Steffen Udluft, Hans-Georg Zimmermann |
| 2007 | ESANN | Neural Rewards Regression for near-optimal policy identification in Markovian and partial observable environments. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ESANN | Explicit Kernel Rewards Regression for data-efficient near-optimal policy identification. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | ICANN | Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification. | Daniel Schneega, Steffen Udluft, Thomas Martinetz |
| 2007 | IJCNN | A Neural Reinforcement Learning Approach to Gas Turbine Control. | Anton Maximilian Schfer, Daniel Schneega, Volkmar Sterzing, Steffen Udluft |
| 2006 | ICANN | Learning Long Term Dependencies with Recurrent Neural Networks. | Anton Maximilian Schfer, Steffen Udluft, Hans-Georg Zimmermann |