Suche

David Pätzel, M. Sc.


Pätzel

Wiss. Mitarbeiter

E-Mail: david.paetzel@informatik.uni-augsburg.de
Telefon: +49 821 598 - 4630
Fax: +49 821 598 - 4627
Raum: 502
Sprechzeiten: nach Vereinbarung
Hausanschrift: Eichleitnerstr. 30
86159 Augsburg


Research interests

My main research is directed towards Learning Classifier Systems (especially XCS and its derivatives), a family of versatile evolutionary rule-based reinforcement learning algorithms. One of the main arguments for their application is being more interpretable than other learning systems such as artificial neural networks. However, we still don't yet fully understand in a formal way which problems LCS are able to learn exactly and why they can learn them—which weakens the argument for them quite a bit. Through my work, I want to develop a more formal understanding of LCS and finally prove several assumptions that were, up to now, only validated experimentally.

Other than that, I'm very interested in

  • reinforcement learning
  • evolutionary machine learning algorithms
  • functional programming, especially using Haskell
  • ways to incoporate a more formal (functional) view into everyday software such as operating systems (NixOS) or window managers (XMonad)
  • free software

Publications

… can be found here.

Teaching

  • Winter 2018: Fundamentals of Organic Computing (Bachelor students' lab)
  • Summer 2018: Organic Computing II (Master students' lab)
  • Winter 2017: Peer-to-Peer and Cloud Computing (Master students' lab)