PhD Theses

1. Marcin Szubert, Coevolutionary Shaping for Reinforcement Learning, 2014 (main supervisor: prof. Krzysztof Krawiec).
   • Best Doctoral Thesis Award in the contest by the Polish Artificial Intelligence Society (“Polskie Stowarzyszenie Sztucznej Inteligencji”), a member of ECCAI.

Master’s Theses

1. Mateusz Kurek, Deep Reinforcement Learning in Keepaway Soccer, 2015.
   • [github]
   • Published as “Heterogeneous Team Deep Q-Learning in Low-Dimensional Multi-Agent Environments“, Computational Intelligence in Games Conference, 2016
2. Aleksander Kędzierski, Tree-search Algorithms for General Video Game AI Competition (pol. “Algorytmy przeszukiwania drzew stanów dla General Video Game AI Competition”), 2015.
   • 6th place (among 55 participants) in CEEC General Video Game AI Competition 2015
3. Tomasz Kuliński, Learning n-tuple networks to play Othello using and CMA-ES
   (pol. “Uczenie sieci n-krotkowych gry w Othello z wykorzystaniem CMA-ES”)
4. Filip Cyrus Bober, On Design of Effective AI Agent for StarCraft, 2014.
5. Piotr Szachewicz, Classification of Motor Imagery for Brain-Computer Interfaces, 2013.
6. Paweł Liskowski, Co-Evolution Versus Evolution with Random Sampling for Acquiring Othello Position Evaluation, 2012.
   • 3rd place in the Polish Information Processing Society contest for the best master’s thesis in Computer Science, 2012.
7. Jarosław Janiszewski, Methods for mind-reading (pol. ”Metody czytania w myślach”), 2012.
8. Marcin Szubert, Coevolutionary Reinforcement Learning and its Application to Othello, 2009 (main supervisor: prof. Krzysztof Krawiec).
   • 2nd place in the Polish Information Processing Society contest for the best master’s thesis in Computer Science, 2009.
9. Paweł Lichocki, “Evolving Players for a Real-Time Strategy Game Using Gene Expression Programming“, 2008 (main supervisor: prof. Krzysztof Krawiec).
   • Resulted in a joint publication: Evolving Teams of Cooperating Agents for Real-Time Strategy Game.

Bachelor’s Theses

1. Michał Kempka, Grzegorz Runc, Jakub Toczek & Marek Wydmuch, “VIZIA: 3D Video Game-base Environment for Research on Learning Agents from Raw Visual Information“, 2016.
   • Lead to ViZDoom platform
   • Published as “ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning“, Computational Intelligence in Games Conference, 2016
2. Dominik Przybyła, A mobile application with a set of exercises to support visual training for visually impaired children (pol. Aplikacja z zestawem ćwiczeń wspomagających trening wzrokowy u dzieci niedowidzących), 2015.
3. Michał Nowicki, Olgierd Pilarczyk, Jakub Wąsikowski, Katarzyna Zjawin, “Gesture Recognition Library for Leap Motion Controller“, 2014.
   • LeapGesture Library on GitHub
   • Google Scholar citations