Martin Müller
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2021
Martin Müller is a Fellow and Canada CIFAR AI Chair at Amii and a Professor of Computing Science at the University of Alberta.
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.
Awards
- 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
Relevant Publications
- O. Randall, T.-h. Wei, R. Hayward and M. Müller (2024). Expected Work Search: Combining Win Rate and Proof Size Estimation. IJCAI.
- F. Kohankhaki, K. Aghakasiri, H. Zhang, T.-h. Wei, C. Gao and M. Müller (2024). Monte Carlo Tree Search in the Presence of Transition Uncertainty. AAAI.
- H. Zhang, C. Xiao, H. Wang, J. Jin, B. Xu & M. Müller. (2023). Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay. ICLR.
- T. Bertram, J. Fürnkranz & M. Müller.(2022). Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess. IEEE Conference on Games (CoG).
Chowdhury, M. S., Müller, M., & You, J. (2020). Guiding CDCL SAT Search via Random Exploration amid Conflict Depression. In AAAI (pp. 1428-1435).