Most reinforcement learning techniques optimize expected utility. However, in various application domains such as finance, sport analytics and medicine, it is often desirable to take into account the risk induced by variability in utility beyond just the mean. In that respect, distributional reinforcement learning provides a nice framework to estimate the entire distribution of utility instead of the mean only. However, modeling distributions instead of point estimates is much more challenging. In this talk, I will first describe a new technique to represent distribution quantiles with rational monotonic splines. Then, I will show how to derive a risk-sensitive game impact metric to evaluate players in professional hockey and soccer.

Bio: Pascal Poupart is a Professor in the David R. Cheriton School of Computer Science at the University of Waterloo, Waterloo (Canada). He is also a Canada CIFAR AI Chair at the Vector Institute and a member of the Waterloo AI Institute. He serves on the advisory board of the AI Institute For Advances in Optimization (2022-present). He served as Research Director and Principal Research Scientist at the Waterloo Borealis AI Research Lab funded by the Royal Bank of Canada (2018-2020). He also served as scientific advisor for ProNavigator (2017-2019), ElementAI (2017-2018) and DialPad (2017-2018). He received the Ph.D. in Computer Science at the University of Toronto (2005). His research focuses on the development of algorithms for Machine Learning with application to Natural Language Processing and Material Design. He is most well-known for his contributions to the development of Reinforcement Learning algorithms. Notable projects that his research team are currently working on include Object-oriented, risk-senstivite and constrained reinforcement learning, Bayesian federated learning, probabilistic deep learning, conversational agents, automated document editing, sport analytics, adaptive satisfiability and material design for CO2 conversion & capture. Pascal Poupart received a Canada CIFAR AI Chair at the Vector Institute (2018-present), outstanding performance awards at the University of Waterloo (2017, 2021), a Cheriton Faculty Fellowship (2015-2018), a best student paper honourable mention (SAT-2017), a silver medal at the SAT-2017 competition, and a gold medal at the SAT-2016 competition.