Johannes Czech

Home * People * Johannes Czech

Johannes Czech

Johannes Czech,
a German computer scientist and Ph.D. student at TU Darmstadt. His research interests include deep learning models in search algorithms such as Monte-Carlo tree search . He is primary author of the UCI compatible chess variant open source engine CrazyAra, with focus on playing Crazyhouse, and its classical chess counterpart ClassicAra. CrazyAra started in summer 2018 as a semester project by Johannes Czech along with Moritz Willig and Alena Beyer for the course Deep Learning: Methods and Architectures at TU Darmstadt, and was entirely written in Python. As subject of his master thesis , Johannes Czech continued the development in porting the engine to C++ and to further apply reinforcement learning to Crazyhouse and other chess variants including Chess960.

Selected Publications

• Johannes Czech (2019). Deep Reinforcement Learning for Crazyhouse. Master thesis, TU Darmstadt, pdf
• Johannes Czech, Moritz Willig, Alena Beyer, Kristian Kersting, Johannes Fürnkranz (2019). Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data. arXiv:1908.06660
• Johannes Czech, Moritz Willig, Alena Beyer, Kristian Kersting, Johannes Fürnkranz (2020). Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data. Frontiers in Artificial Intelligence
• Johannes Czech, Patrick Korus, Kristian Kersting (2020). Monte-Carlo Graph Search for AlphaZero. arXiv:2012.11045
• Johannes Czech, Patrick Korus, Kristian Kersting (2021). Improving AlphaZero Using Monte-Carlo Graph Search. Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling, Vol. 31, pdf

External Links

• TU Darmstadt | Johannes Czech
• QueensGambit (Johannes Czech) · GitHub
• Darmstädter Studenten entwickeln Schach-Bot by Karin Walz, Echo, April 02, 2019 (German)

References

Up one level