Expertise
Mathematics
- Effective Sample Size
- Explicit Dependence
Computer Science
- Dependence Structure
Organisations
My research concerns the use of statistical learning theory (amongst other tools) to understand the generalization ability of deep reinforcement learning algorithms. I am currently working on bridging the gap between deep reinforcement learning theory and practice; to this end, my work tries to remove unrealistic assumptions or replace them with realistic assumptions in general deep reinforcement learning settings.
Publications
2026
Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under τ-Mixing (2026)[Working paper › Preprint]. ArXiv.org (Submitted). Halgryn, L., Meylahn, J. M., Langer, S. & Hahn, E. M.https://doi.org/10.48550/arXiv.2605.06373
Research profiles
Courses academic year 2025/2026
Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.
Courses academic year 2024/2025
Address

University of Twente
Zilverling (building no. 11), room 4054
Hallenweg 19
7522 NH Enschede
Netherlands
University of Twente
Zilverling 4054
P.O. Box 217
7500 AE Enschede
Netherlands