Martin Müller’s main area of research is modern heuristic search, with its complex interactions between search, knowledge, simulations and machine learning. Application areas include game tree search, domain-independent planning, combinatorial games, and boolean satisfiability (SAT) solving. Müller has worked on computer Go for thirty years. He is known for leading the development of the open source program Fuego. In 2009, this program became the first to win a 9×9 Go game on even terms against a top-ranked professional human player. With his students and colleagues, Müller has developed a series of successful game-playing programs, planning systems, and SAT solvers.
- DeepMind Chair in Artificial Intelligence, University of Alberta, 2019
- Fellow, Alberta Machine Intelligence Institute, 2019
- Outstanding paper award, AAAI, 2018
- ACM ICPC coach award, 2012
- Winner, 4th UEC Cup (Computer Go contest), 2010
- Chowdhury, M. S., Müller, M., & You, J. (2020). Guiding CDCL SAT Search via Random Exploration amid Conflict Depression. In AAAI (pp. 1428-1435).
- Xiao, C., Mei, J., & Müller, M. (2018, April). Memory-augmented monte carlo tree search. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 32, No. 1).
- Xie, F., Müller, M., Holte, R., & Imai, T. (2014, June). Type-based exploration with multiple search queues for satisficing planning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 28, No. 1).
- Silver, D., Sutton, R. S., & Müller, M. (2012). Temporal-difference search in computer Go. Machine learning, 87(2), 183-219.
- Nakhost, H., & Müller, M. (2009, June). Monte-Carlo exploration for deterministic planning. In Twenty-First International Joint Conference on Artificial Intelligence.
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.