Steffen Udluft

72 papers A* 2A 1B 16C 2Misc 2Journal 34Unranked 14

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	From Classical Data to Quantum Advantage - Quantum Policy Evaluation on Quantum Hardware. CoRR Daniel Hein, Simon Wiedemann, Markus Baumann, Patrik Felbinger, Justin Klein, Maximilian Schieder, Jonas Stein, Daniëlle Schuman, Thomas Cope, Steffen Udluft
2025	J	`jnl`	Is Q-learning an Ill-posed Problem? CoRR Philipp Wissmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler
2025	—	`conf`	Neural-Anova: Analytical Model Decomposition Using Automatic Integration. MLSP Steffen Limmer, Steffen Udluft, Clemens Otte
2025	J	`jnl`	Variational Quantum Circuits in Offline Contextual Bandit Problems. CoRR Lukas Schulte, Daniel Hein, Steffen Udluft, Thomas A. Runkler
2024	Misc	`conf`	Model-Based Offline Quantum Reinforcement Learning. QCE Simon Eisenmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler
2024	J	`jnl`	Model-based Offline Quantum Reinforcement Learning. CoRR Simon Eisenmann, Daniel Hein, Steffen Udluft, Thomas A. Runkler
2024	J	`jnl`	Neural-ANOVA: Model Decomposition for Interpretable Machine Learning. CoRR Steffen Limmer, Steffen Udluft, Clemens Otte
2024	J	`jnl`	TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning. CoRR Batikan Bora Ormanci, Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2024	B	`conf`	Why long model-based rollouts are no reason for bad Q-value estimates. ESANN Philipp Wissmann, Daniel Hein, Steffen Udluft, Volker Tresp
2024	J	`jnl`	Why long model-based rollouts are no reason for bad Q-value estimates. CoRR Philipp Wissmann, Daniel Hein, Steffen Udluft, Volker Tresp
2023	B	`conf`	Automatic Trade-off Adaptation in Offline RL. ESANN Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2023	J	`jnl`	Automatic Trade-off Adaptation in Offline RL. CoRR Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2023	—	`conf`	Learning Control Policies for Variable Objectives from Offline Data. SSCI Marc Weber, Phillip Swazinna, Daniel Hein, Steffen Udluft, Volkmar Sterzing
2023	J	`jnl`	Learning Control Policies for Variable Objectives from Offline Data. CoRR Marc Weber, Phillip Swazinna, Daniel Hein, Steffen Udluft, Volkmar Sterzing
2023	J	`jnl`	Quantum Policy Iteration via Amplitude Estimation and Grover Search - Towards Quantum Advantage for Reinforcement Learning. Trans. Mach. Learn. Res. Simon Wiedemann, Daniel Hein, Steffen Udluft, Christian B. Mendl
2023	A*	`conf`	User-Interactive Offline Reinforcement Learning. ICLR Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2023	Misc	`conf`	Workshop Summary: Quantum Machine Learning. QCE Volker Tresp, Steffen Udluft, Daniel Hein, Werner Hauptmann, Martin Leib, Christopher Mutschler, Daniel D. Scherer, Wolfgang Mauerer
2022	J	`jnl`	Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning. CoRR Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
2022	J	`jnl`	Quantum Policy Iteration via Amplitude Estimation and Grover Search - Towards Quantum Advantage for Reinforcement Learning. CoRR Simon Wiedemann, Daniel Hein, Steffen Udluft, Christian B. Mendl
2022	—	`conf`	Safe Policy Improvement Approaches and Their Limitations. ICAART (Revised Selected Paper Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
2022	J	`jnl`	Safe Policy Improvement Approaches and their Limitations. CoRR Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
2022	—	`conf`	Safe Policy Improvement Approaches on Discrete Markov Decision Processes. ICAART (2) Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
2022	J	`jnl`	Safe Policy Improvement Approaches on Discrete Markov Decision Processes. CoRR Philipp Scholl, Felix Dietrich, Clemens Otte, Steffen Udluft
2022	J	`jnl`	User-Interactive Offline Reinforcement Learning. CoRR Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2021	B	`conf`	Behavior Constraining in Weight Space for Offline Reinforcement Learning. ESANN Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
2021	J	`jnl`	Behavior Constraining in Weight Space for Offline Reinforcement Learning. CoRR Phillip Swazinna, Steffen Udluft, Daniel Hein, Thomas A. Runkler
2021	—	`conf`	Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning. SSCI Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2021	J	`jnl`	Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning. CoRR Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2021	J	`jnl`	Overcoming model bias for robust offline deep reinforcement learning. Eng. Appl. Artif. Intell. Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2020	J	`jnl`	Overcoming Model Bias for Robust Offline Deep Reinforcement Learning. CoRR Phillip Swazinna, Steffen Udluft, Thomas A. Runkler
2019	—	`conf`	Generating interpretable reinforcement learning policies using genetic programming. GECCO (Companion) Daniel Hein, Steffen Udluft, Thomas A. Runkler
2018	A*	`conf`	Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. ICML Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
2018	J	`jnl`	Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming. CoRR Daniel Hein, Steffen Udluft, Thomas A. Runkler
2018	—	`conf`	Generating interpretable fuzzy controllers using particle swarm optimization and genetic programming. GECCO (Companion) Daniel Hein, Steffen Udluft, Thomas A. Runkler
2018	J	`jnl`	Interpretable policies for reinforcement learning by genetic programming. Eng. Appl. Artif. Intell. Daniel Hein, Steffen Udluft, Thomas A. Runkler
2018	B	`conf`	Sensitivity analysis for predictive uncertainty. ESANN Stefan Depeweg, José Miguel Hernández-Lobato, Steffen Udluft, Thomas A. Runkler
2017	J	`jnl`	A Benchmark Environment Motivated by Industrial Control Problems. CoRR Daniel Hein, Stefan Depeweg, Michel Tokic, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
2017	—	`conf`	A benchmark environment motivated by industrial control problems. SSCI Daniel Hein, Stefan Depeweg, Michel Tokic, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
2017	J	`jnl`	Batch Reinforcement Learning on the Industrial Benchmark: First Experiences. CoRR Daniel Hein, Steffen Udluft, Michel Tokic, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
2017	B	`conf`	Batch reinforcement learning on the industrial benchmark: First experiences. IJCNN Daniel Hein, Steffen Udluft, Michel Tokic, Alexander Hentschel, Thomas A. Runkler, Volkmar Sterzing
2017	J	`jnl`	Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems. CoRR Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
2017	J	`jnl`	Interpretable Policies for Reinforcement Learning by Genetic Programming. CoRR Daniel Hein, Steffen Udluft, Thomas A. Runkler
2017	—	`conf`	Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. ICLR (Poster) Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
2017	J	`jnl`	Particle swarm optimization for generating interpretable fuzzy reinforcement learning policies. Eng. Appl. Artif. Intell. Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
2016	J	`jnl`	Introduction to the "Industrial Benchmark". CoRR Daniel Hein, Alexander Hentschel, Volkmar Sterzing, Michel Tokic, Steffen Udluft
2016	J	`jnl`	Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. CoRR Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft
2016	J	`jnl`	Particle Swarm Optimization for Generating Fuzzy Reinforcement Learning Policies. CoRR Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
2016	J	`jnl`	Reinforcement Learning with Particle Swarm Optimization Policy (PSO-P) in Continuous State and Action Spaces. Int. J. Swarm Intell. Res. Daniel Hein, Alexander Hentschel, Thomas A. Runkler, Steffen Udluft
2015	J	`jnl`	Exploiting similarity in system identification tasks with recurrent neural networks. Neurocomputing Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler
2014	B	`conf`	Exploiting similarity in system identification tasks with recurrent neural networks. ESANN Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Alexander Hentschel, Thomas A. Runkler
2014	C	`conf`	Regularized Recurrent Neural Networks for Data Efficient Dual-Task Learning. ICANN Sigurd Spieckermann, Siegmund Düll, Steffen Udluft, Thomas A. Runkler
2013	B	`conf`	Ensembles for Continuous Actions in Reinforcement Learning. ESANN Siegmund Duell, Steffen Udluft
2012	J	`jnl`	Datenbasierte Optimalsteuerung mit neuronalen Netzen und dateneffizientem Reinforcement Learning. Autom. Thomas A. Runkler, Steffen Udluft, Siegmund Düll
2012	B	`conf`	Recurrent Neural State Estimation in Domains with Long-Term Dependencies. ESANN Siegmund Duell, Lina Weichbrodt, Alexander Hans, Steffen Udluft
2012	—	`ch.`	Solving Partially Observable Reinforcement Learning Problems with Recurrent Neural Networks. Neural Networks: Tricks of the Trade (2nd ed.) Siegmund Duell, Steffen Udluft, Volkmar Sterzing
2011	—	`conf`	Agent self-assessment: Determining policy quality without execution. ADPRL Alexander Hans, Siegmund Duell, Steffen Udluft
2011	B	`conf`	Ensemble Usage for More Reliable Policy Identification in Reinforcement Learning. ESANN Alexander Hans, Steffen Udluft
2010	C	`conf`	Ensembles of Neural Networks for Robust Reinforcement Learning. ICMLA Alexander Hans, Steffen Udluft
2010	B	`conf`	The Markov Decision Process Extraction Network. ESANN Siegmund Duell, Alexander Hans, Steffen Udluft
2010	A	`conf`	Uncertainty Propagation for Efficient Exploration in Reinforcement Learning. ECAI Alexander Hans, Steffen Udluft
2009	J	`jnl`	Dateneffizientes Reinforcement-Learning. Künstliche Intell. Volkmar Sterzing, Steffen Udluft
2009	—	`conf`	Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data. ICANN (1) Alexander Hans, Steffen Udluft
2008	J	`jnl`	Learning long-term dependencies with recurrent neural networks. Neurocomputing Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann
2008	B	`conf`	Safe exploration for reinforcement learning. ESANN Alexander Hans, Daniel Schneegaß, Anton Maximilian Schäfer, Steffen Udluft
2008	B	`conf`	Uncertainty propagation for quality assurance in Reinforcement Learning. IJCNN Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
2007	B	`conf`	A Neural Reinforcement Learning Approach to Gas Turbine Control. IJCNN Anton Maximilian Schäfer, Daniel Schneegaß, Volkmar Sterzing, Steffen Udluft
2007	B	`conf`	Explicit Kernel Rewards Regression for data-efficient near-optimal policy identification. ESANN Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
2007	—	`conf`	Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification. ICANN (1) Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
2007	B	`conf`	Neural Rewards Regression for near-optimal policy identification in Markovian and partial observable environments. ESANN Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
2007	B	`conf`	The Recurrent Control Neural Network. ESANN Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann
2006	—	`conf`	Kernel Rewards Regression: An Information Efficient Batch Policy Iteration Approach. Artificial Intelligence and Applications Daniel Schneegaß, Steffen Udluft, Thomas Martinetz
2006	—	`conf`	Learning Long Term Dependencies with Recurrent Neural Networks. ICANN (1) Anton Maximilian Schäfer, Steffen Udluft, Hans-Georg Zimmermann