Steffen Udluft

Siemens (Germany) — Germany

Computer Science · Physical Sciences

25h-index2.0kcitations98works0.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(42), Particle physics theoretical and experimental studies(18), High-Energy Particle Collisions Research(18), Quantum Chromodynamics and Particle Interactions(16), Neural Networks and Applications(11)

Publications80 total

Neural-Anova: Analytical Model Decomposition Using Automatic Integration
2025· 1 cited
Variational Quantum Circuits in Offline Contextual Bandit Problems
2025Open Access
First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
2025
Learning Control with Simulated Variational Quantum Policies in a Surrogate Cart-Pole Environment
2025
From Classical Data to Quantum Advantage – Quantum Policy Evaluation on Quantum Hardware
2025Open Access
First Experience with Real-Time Control Using Simulated VQC-Based Quantum Policies
arXiv (Cornell University)·2025Open Access
Is Q-learning an Ill-posed Problem?
arXiv (Cornell University)·2025Open Access
TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning
2025· 1 citedOpen Access
Is Q-learning an Ill-posed Problem?
2025Open Access
TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Model-Based Offline Quantum Reinforcement Learning
2024· 4 cited
Neural-ANOVA: Analytical Model Decomposition using Automatic Integration
arXiv (Cornell University)·2024· 1 citedOpen Access
Why long model-based rollouts are no reason for bad Q-value estimates
arXiv (Cornell University)·2024· 1 citedOpen Access
Model-based Offline Quantum Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Why long model-based rollouts are no reason for bad Q-value estimates
2024Open Access
Learning Control Policies for Variable Objectives from Offline Data
2023· 1 cited
Workshop Summary: Quantum Machine Learning
2023
Learning Control Policies for Variable Objectives from Offline Data
arXiv (Cornell University)·2023Open Access
Automatic Trade-off Adaptation in Offline RL
arXiv (Cornell University)·2023Open Access
Automatic Trade-off Adaptation in Offline RL
2023Open Access
page 1 of 4Next →

Frequent Co-authors

Thomas A. Runkler(17), Stefan Depeweg(9), Alexander Hans(9), Daniel Hein(9), José Miguel Hernández-Lobato(7), Daniel Schneegaß(7), Alexander Hentschel(7), Finale Doshi‐Velez(6), Siegmund Duell(5), Phillip Swazinna(5), Volkmar Sterzing(4), Thomas Martinetz(4), Anton Maximilian Schäfer(3), Anton Maximilian Schaefer(3), Hans-Georg Zimmermann(3), Felix Dietrich(3), Clemens Otte(3), Michel Tokic(2), Sigurd Spieckermann(2), Siegmund Düll(2)