Lukas Zierahn

Lukas Zierahn

Postdoc at CWI & Booking.com · lukas.zierahn@gmail.com

I am working with Wouter Koolen and Christina Katsimerou on Best-Arm Identification. Previously, I obtained my PhD as part of the ELLIS program supervised by Nicolò Cesa-Bianchi and Gergely Neu in October 2026.

My research interest include Bandits and Reinforcement Learning, both for regret minimization and pure exploration.

In my free time I enjoy playing guitar and chess.

Lukas Zierahn

Selected Publications

  • Zierahn, L., van der Hoeven, D., Lancewicki, T., Rosenberg, A., & Cesa-Bianchi, N. (2025). A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs. Journal of Machine Learning Research, 26(104), 1-60. (paper)

  • Zierahn, L., van der Hoeven, D., Cesa-Bianchi, N., & Neu, G. (2023). Nonstochastic Contextual Combinatorial Bandits. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, 8771-8813. (paper)