About
Appointed Canada CIFAR AI Chair – 2021
Neil Burch works on decision making in imperfect information environments, where different agents know different things about the world. What are the best choices an agent can make in theory? What are practical algorithms for making decisions? How close are those things? He is particularly interested in applying search to these problems, using computation at decision time to make better decisions.
Awards
- Development of depth-limited imperfect information search, no-limit agent beat professional poker players, 2016
- Solved checkers, 2007
Relevant Publications
Kovařík, V., Schmid M., Burch N., Bowling M., Lisý V., (2022). Rethinking formal models of partially observable multiagent decision making.
Julien Perolat et al. (2022). Mastering the game of Stratego with model-free multiagent reinforcement learning.
Bard, N., Foerster, J.N, Chandar, S., Burch, N., Lanctot, M., Song, H. F., Parisotto, E., Dumoulin, V., Moitra, S., Hughes, E., Dunning, I., Mourad, S., Larochelle, H., Bellemare, M.G., Bowling, M. (2019). The Hanabi challenge: A new frontier for AI research, 32.
Moravčík, M., Schmid, M., Burch, N., Lisý, V, Morrill, D., Bard, N., Davis, T., Waugh, K., Johanson, M., Bowling, M. (2017). DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker.
Schmid, M., Burch, N., Lanctot, M., Moravcik, M., Kadlec, R., Bowling, M. (2018). Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games Using Baselines.
Bowling, M., Burch, N., Johanson, M., Tammelin, O. (2015). Heads-up Limit Hold’em Poker is Solved.