Alberta Machine Intelligence Institute

Fellow & Canada CIFAR AI Chair

Martin Müller

Academic Affiliations

Professor – University of Alberta (Computing Science)

Industry & Research Affiliations

DeepMind Chair in Artificial Intelligence – University of Alberta

Focus

Artificial intelligence; game tree search algorithms; machine learning; heuristic search; deep learning; reinforcement learning; combinatorial game theory; monte carlo tree search; planning; games; computer Go

Martin Müller is interested in developing efficient search methods for hard problems.

Search, plan, Go!

Martin Müller is interested in developing efficient search methods for hard problems. He and his research team work on understanding and improving Monte Carlo tree search, exploring and sampling in reinforcement learning, exploration in SAT, search and deep learning for Hex, and combinatorial game theory – especially developing efficient algorithms that combine search and subgame decomposition. He also works on domain-independent planning, random walk planning and motion planning and random sampling from time-changing discrete distributions. Martin and his team have produced programs and algorithms for the games of Go, Amazons, Clobber and Hex. Many of his algorithms use all three of the modern heuristic search methods: search, knowledge and randomized simulations. Martin was the academic co-supervisor (along with Richard S. Sutton) of David Silver, who went on to become head of reinforcement learning at DeepMind and lead researcher on AlphaGo.

Martin is a Fellow and Canada CIFAR AI Chair at Amii and a Professor of Computing Science and the DeepMind Chair in Artificial Intelligence at the University of Alberta. He is also a Fellow at Amii. He has also held the role of Associate Chair (Research) for the Department of Computing Science. Martin has been the academic supervisor for over 50 students and visiting researchers – with a number of those students receiving national and international awards for their work. Martin has published nearly 120 papers in venues such as the conference for the Association for the Advancement of Artificial Intelligence (AAAI), the Institute of Electrical and Electronics Engineers (IEEE) Transactions on Games, and the International Joint Conference on Artificial Intelligence (IJCAI), among others. Martin has delivered talks at international conferences including IJCAI, AAAI and IEEE as well as for organizations such as Baidu Research and the Tencent AI Lab.

Martin is a Professor of Computing Science and the DeepMind Chair in Artificial Intelligence at the University of Alberta.

Latest News