Portrait of David Meger

David Meger

Associate Academic Member
david.meger@mila.quebec
Canada CIFAR AI Chair
Associate Professor, McGill University, School of Computer Science
Research Topics
Computer Vision
Reinforcement Learning
Website
Google Scholar

Biography

David Meger is an associate professor at McGill University’s School of Computer Science.

He co-directs the Mobile Robotics Lab within the Centre for Intelligent Machines, one of Canada's largest and longest-running robotics research groups. He was the general chair of Canada’s first joint CS-CAN conference in 2023.

Meger's research contributions include visually guided robots powered by active vision and learning, deep reinforcement learning models that are widely cited and used by researchers and industry worldwide, and field robotics that allow for autonomous deployment underwater and on land.

Current Students

William Bonilla
PhD - McGill University
william.bonilla@mila.quebec
Github
Valliappan Chidambaram Adaikkappan
PhD - McGill University
chidambv@mila.quebec
Github
Google Scholar
Wesley Chung
PhD - McGill University
Co-supervisor :
Doina Precup
chungwes@mila.quebec
Mathias Desrochers
Master's Research - McGill University
mathias.desrochers@mila.quebec
Website
Farnoosh Faraji
PhD - McGill University
Co-supervisor :
Gregory Dudek
farnoosh.faraji@mila.quebec
Github
Google Scholar
Charles-Étienne Fréchette
Master's Research - McGill University
charles.etienne.frechette@gmail.com
Anas Houssaini
Master's Research - McGill University
Co-supervisor :
Hsiu-Chin Lin
anas.houssaini@mila.quebec
Github
Brik Meza Pinedo
Master's Research - McGill University
brik.meza@mail.mcgill.ca
Website
Github
LinkedIn
Arian Sargazi
PhD - McGill University
arian.sargazi@mila.quebec
Junming(Clark) Shi
Master's Research - McGill University
junming.shi@mila.quebec
Github
Steven Wang
Master's Research - McGill University
zhizun.wang@mail.mcgill.ca

Publications

OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Peter Henderson
Wei-Di Chang
Pierre-Luc Bacon
David Meger
Joelle Pineau
Doina Precup
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward fu… (see more)nction can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning.
2018-04-28
Proceedings of the AAAI Conference on Artificial Intelligence (published)
doi.org
arxiv.org