Portrait of Audrey Durand

Audrey Durand

Associate Academic Member
audrey.durand@ift.ulaval.ca
Canada CIFAR AI Chair
Assistant Professor, Université Laval, Department of Computer Science and Software Engineering
Research Topics
Online Learning
Reinforcement Learning
Website
Google Scholar
X

Biography

Audrey Durand is an assistant professor in the Department of Computer Science and Software Engineering and in the Department of Electrical and Computer Engineering at Université Laval.

She specializes in algorithms that learn through interaction with their environment using reinforcement learning, and is particularly interested in leveraging these approaches in health-related applications.

Current Students

Yohaï-Eliel Berreby
PhD - McGill University
me@yberreby.com
Website
Github
Google Scholar
Baptiste Bonin
Master's Research - Université Laval
Hugo Delhaye
Master's Research - Université de Montréal
Principal supervisor :
Lune Bellec
Maxime Heuillet
PhD - Université Laval
Bruno Joyal
Master's Research - Université Laval
Alexandre Larouche
PhD - Université Laval
Github
Google Scholar
Randy Lefebvre
Master's Research - Université Laval
Kaoutar Mimouni
Master's Research - Université Laval
Hadi Moazen
PhD - Université Laval

Publications

Temporal Regularization for Markov Decision Process
Pierre Thodoroff
Audrey Durand
Joelle Pineau
Doina Precup
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensiona… (see more)l domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus on spatial (perceptual) regularization. Yet in reinforcement learning, due to the nature of the Bellman equation, there is an opportunity to also exploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization. We formally characterize the bias induced by this technique using Markov chain concepts. We illustrate the various characteristics of temporal regularization via a sequence of simple discrete and continuous MDPs, and show that the technique provides improvement even in high-dimensional Atari games.