Norm Ferns
Research
My primary research has been in reinforcement learning, specifically in studying approximation, similarity, and explainability in Markov decision processes both in academic and industrial settings. More generally, I am interested in a variety of topics in mathematics and computer science, including artificial intelligence, machine learning, formal verification, and computational neuroscience.
My graduate studies were carried out at McGill University's Reasoning and Learning Lab under the supervision of Professor Prakash Panangaden and Professor Doina Precup. At PrakashFest in 2014, Professor Precup gave a very nice presentation typical of the work we did together.
More recently, I have been investigating applications of the reinforcement learning framework to team-based invasion sports at Sportlogiq. Here I am giving a broad overview of this work at the Montreal AI Symposium in 2017.
E-mail: norm [dot] ferns [at] normferns [dot] com
Selected Publications
Ferns, N., and Precup, D. 2014. Bisimulation Metrics are Optimal Value Functions. In the 30th Conference on Uncertainty in Artificial Intelligence (Quebec City, Quebec, Canada July 23 - 27, 2014). AUAI Press, Corvallis, Oregon, 210-219. Acceptance rate 33%. [PDF]
Ferns, N., Knight, S., and Precup, D. 2014. Bisimulation for Markov Decision Processes through Families of Functional Expressions. In Horizons of the Mind. A Tribute to Prakash Panangaden: Essays Dedicated to Prakash Panangaden on the Occasion of His 60th Birthday. Springer International Publishing, 2014. p 319-342 (Lecture Notes in Computer Science; Vol. 8464). [PDF]
Ferns, N., Panangaden, P., and Precup, D. 2011. Bisimulation Metrics for Continuous Markov Decision Processes. In SIAM Journal on Computing. Vol. 40, No. 6, 1662-1714. [PDF]
Ferns, N., Castro, P., Panangaden, P., and Precup, D. 2006. Methods for Computing State Similarity in Markov Decision Processes. In Proceedings of the 22nd Conference on Uncertainty in Artificial intelligence (Cambridge, MA, USA July 13 - 16, 2006). AUAI Press, Arlington, Virginia, 174-181. Acceptance rate 32%. [PDF]
Ferns, N., Panangaden, P., and Precup, D. 2005. Metrics for Markov Decision Processes with Infinite State Spaces. In Proceedings of the 21st Conference on Uncertainty in Artificial intelligence (Edinburgh, Scotland, July 26 - 29, 2005). AUAI Press, Arlington, Virginia, 201-208. Acceptance rate 34%. [PDF]
Bouchard-Côté, A., Ferns, N., Panangaden, P., and Precup, D. 2005. An Approximation Algorithm for Labelled Markov Processes: Towards Realistic Approximation. In Proceedings of the Second International Conference on the Quantitative Evaluation of Systems (QEST 05) (September 19 - 22, 2005). QEST. IEEE Computer Society, Washington, DC, 54-62. Acceptance rate 30%. [PDF]
Ferns, N., Panangaden, P., and Precup, D. 2004. Metrics for Finite Markov Decision Processes. In Proceedings of the 20th Conference on Uncertainty in Artificial intelligence (Banff, Canada, July 07 - 11, 2004). ACM International Conference Proceeding Series, vol. 70. AUAI Press, Arlington, Virginia, 162-169. Acceptance rate 30%. [PDF]
Hobbies
I love spending time with my wife and kids - whether we're building Lego sets together or playing board games or solving puzzles or enjoying the adventures of Sharpe and Harper, it's just the best. I am also, in no particular order, interested in the follow: weight training and hiking, politics, digital trends, cult and horror films, and almost all things Spider-Man.