Institut für Informationsverarbeitung (TNT)

Yannik Mahlau studied computer science at Leibniz University Hannover. He completed his master's degree in September 2023 with the thesis "AlphaZero for Simultaneous Perfect-Information Games".

Research topics:

Reinforcement Learning
Game Theory
Graph Neural Networks
Inverse Design and Optical Simulations

If you are interested in any of these topics for a student position, bachelor's thesis, or master's thesis, feel free to contact me (<lastname>@tnt.uni-hannover.de)

Publications

Show selected publications only

Yannik Mahlau, Yannick Augenstein, Tyler W. Hughes, Marius Lindauer, Bodo Rosenhahn
Gradient-informed Bayesian and interior point optimization for efficient inverse design in nanophotonics
Opt. Express, Optica Publishing Group, Vol. 34, No. 13, pp. 23160--23174, June 2026
(arXiv.org, GitHub) BibTeX
Yannik Mahlau, Frederik Schubert, Lukas Berg, Bodo Rosenhahn,
FDTDX: High-Performance Open-Source FDTD Simulation with Automatic Differentiation
Journal of Open Source Software, The Open Journal, Vol. 11, No. 117, p. 8912, January 2026
(pdf) BibTeX
Yannik Mahlau, Lukas Berg, Bodo Rosenhahn
Numerical field optimization for enhanced efficiency in time-reversible gradient computation of open-source GPU-accelerated FDTD simulations
Computational Optics, SPIE, 2026, edited by Andreas Erdmann and Nikolai P. Schmitt and Daniel G. Smith
(arXiv.org) BibTeX
Frederik Schubert, Yannik Mahlau, Konrad Bethmann, Fabian Hartmann, Reinhard Caspary, Marco Munderloh, Jörn Ostermann, Bodo Rosenhahn
Quantized Inverse Design for Photonic Integrated Circuits
ACS Omega, January 2025
(arXiv.org) BibTeX
Yannik Mahlau, Frederik Schubert, Konrad Bethmann, Reinhard Caspary, Antonio Calà Lesina, Marco Munderloh, Jörn Ostermann, Bodo Rosenhahn
A flexible framework for large-scale FDTD simulations: open-source inverse design for 3D nanostructures
Preprint, January 2025
(arXiv.org) BibTeX
Konrad Bethmann, Yannik Mahlau, Frederik Schubert, Marco Munderloh, Bodo Rosenhahn, Bernhard Roth, Jörn Ostermann
Inverse design of robust out-of-plane coupling elements
proceedings Photonics West, January 2025
BibTeX
Yannik Mahlau, Maximilian Schier, Christoph Reinders, Frederik Schubert, Marco Bügling, Bodo Rosenhahn
Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits
Reinforcement Learning Journal, Vol. 6, pp. 1794--1815, 2025
(pdf) BibTeX
Yannik Mahlau, Frederik Schubert, Bodo Rosenhahn,
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
Proceedings of the 41st International Conference on Machine Learning (ICML), July 2024
(arXiv.org) BibTeX