Education Activities

This page summarises my education activities and provides information for prospective thesis/internship students.

Courses

The following is a list of courses in which I have been involved in coordinating, giving lectures, labs, and/or assessment:

  • 2024: Lecturer & Coordinator in Reinforcement Learning course (Master’s program) at Maastricht University.
  • 2023: Lecturer in Stochastic Decision Making course (Master’s program) at Maastricht University.
  • 2019 - 2023: Lecturer in Intelligent Search & Games course (Master’s program) at Maastricht University.
  • 2016 - 2019: Assistant in Advanced Concepts in Machine Learning course (grading presentations and reports) at Maastricht University.

Prospective Students

If you are a student at Maastricht University’s Department of Advanced Computing Sciences, and are potentially interested in having me serve as first supervisor for your B.Sc. or M.Sc. thesis, or an internship, please contact me by sending a mail to my UM email address. I recommend to contact me early, as I usually get approached by many more students than I can accept per semester. Make sure to include (preferably in a neatly organised list, not hidden inside a huge wall of text):

  • Whether it is for B.Sc. thesis, M.Sc. thesis, an internship, or anything else.
  • When you expect to start your project (month + year).
  • If they are already close: any deadlines you have in relation to this request (e.g., deadline by which you need to submit a project proposal to the Board of Examiners).
  • Any ideas or preferences you may already have for a topic or research direction. It is fine if you have no ideas (or multiple), and would like to discuss / get advice.
  • If you already know that you have ambitions to potentially continue with a Ph.D. / academic career in the future, and have early indicators of excellent academic performance (e.g., exceptionally good grades in courses relevant to your topic(s) of interest), let me know. Then I can try to help think of topics with high likelihood (potential + feasibility) for publication, to strengthen your academic CV.
  • Any other remarks you have.
  • Any questions you already have for me.

My own main areas of expertise and interest include the following list (not necessarily exhaustive). I prefer to supervise projects that match up with at least one of these areas. It is not at all necessary to combine all or multiple of them: any one is fine. Feel free to also inquire about topics outside of this list, though I will only consider supervising them if I still feel confident that I would be able to perform well as a supervisor:

  • Reinforcement Learning (any application domain).
  • Search algorithms such as Monte-Carlo Tree Search, Minimax-based algorithms, and A* (any application domain).
  • Multi-Armed Bandits (empirical research more so than purely theoretical analyses such as proving regret bounds).
  • AI for (general) game playing.
  • Video games.
  • Adaptation to adversaries in other applications of AI (e.g., credit card fraud detection).
  • Applications of AI / Data Mining to eSports.

At the bottom of this page, I have a list of current and former students for whom I act / have acted as first supervisor, who have also agreed to have their name listed. I am not going to spread their email addresses all over the internet, but if you can find ways to contact them, you may try to do so if you first want to hear about their experience with my supervision.

Current and Former Students

The following is a list of students for whom I have served (or am currently serving) as first supervisor for their B.Sc. thesis, M.Sc. thesis, or internship during their M.Sc. Only includes students who have agreed to be listed. Does not include students where I acted as second supervisor and/or examiner (which I have been doing since 2019).

M.Sc. Thesis Students

  • Alexandra Gianzina (2024)

M.Sc. Internship Students

  • Dimitar Sladić (2024)

B.Sc. Thesis Students

  • Alexander George Padula (2024): “Reinforcement Learning from Explicitly Programmed Reward Signals”
  • Dominic Sagers (2024): “Sequential Halving without Predetermined Budgets in Monte-Carlo Tree Search”