Michael Bowling
About
Appointed Canada CIFAR AI Chair – 2021
Michael Bowling is a full professor at the University of Alberta and a Research Scientist at DeepMind in Edmonton, AB. He is also a principal investigator in the Reinforcement Learning and Artificial Intelligence (RLAI) Lab and leader of the Computer Poker Research Group – both at the University of Alberta.
He is fascinated by the problem of how computers can learn to play games through experience. He is best known for his work in poker, most notably on two milestone advances, both published in Science: Cepheus ‘essentially’ solved the game of heads-up limit Texas hold’em in 2015, and in late 2016, DeepStack became the first AI to beat human professionals at heads-up no-limit Texas hold’em. Both systems represent theoretical leaps forward in the world of imperfect (or hidden) information games. In leading the development of the Arcade Learning Environment, which launched in 2013, Bowling played a pivotal role in the adoption of Atari as a key challenge problem and testbed for AI researchers across the world. The Arcade Learning Environment was instrumental in establishing the subfield of deep reinforcement learning.
Awards
- Faculty of Science Research Fellowship, University of Alberta, 2017–2022
- Faculty of Science Research Award, University of Alberta, 2014
- Faculty of Science Innovation in Teaching Award, University of Alberta, 2014
- Honourable Mention for Alan Blizzard Award, Society for Teaching and Learning in Higher Education, 2011
- Departmental Research Award, University of Alberta, 2010
Relevant Publications
- Machado, MC., Barreto, A., Precup, D., & Bowling, M. (2023). Temporal abstraction in reinforcement learning with the successor representation. Journal of Machine Learning Research, 24(80), 1-69.
- Bowling, M., Martin, JD., Abel, D., & Dabney W. (2022). Settling the Reward Hypothesis. International Conference on Machine Learning.
- Bowling, M. (2020). The Hanabi challenge: A new frontier for AI research.
- Bowling, M., Burch, N., Johanson, M., & Tammelin, O. (2015). Heads-up limit hold’em poker is solved. Science, 347(6218), 145-149.
- Moravčík, M., Schmid, M., Burch, N., Lisý, V., Morrill, D., Bard, N., … & Bowling, M. (2017). Deepstack: Expert-level artificial intelligence in heads-up no-limit poker. Science, 356(6337), 508-513.
- Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013). The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 47, 253-279.