Portrait of David Meger

David Meger

Associate Academic Member
Associate Professor, McGill University, School of Computer Science
Research Topics
Computer Vision
Reinforcement Learning

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

Julie Alhosh
Master's Research - McGill University
juliealhosh@gmail.com
Website
Github
Google Scholar
Rambod Azimi
Collaborating researcher - McGill University
Principal supervisor :
Samira Ebrahimi Kahou
Website
Github
Google Scholar
William Bonilla
PhD - McGill University
Github
Valliappan Chidambaram Adaikkappan
PhD - McGill University
Github
Google Scholar
Wesley Chung
PhD - McGill University
Co-supervisor :
Doina Precup
Farnoosh Faraji
PhD - McGill University
Co-supervisor :
Gregory Dudek
Github
Google Scholar
Anas Houssaini
Master's Research - McGill University
Co-supervisor :
Hsiu-Chin Lin
Github
Zina Kamel
Master's Research - McGill University
Co-supervisor :
Hsiu-Chin Lin
Sahand Rezaei-Shoshtari
PhD - McGill University
Principal supervisor :
Doina Precup
Website
Github
Google Scholar
Arian Sargazi
PhD - McGill University
Steven Wang
Master's Research - McGill University
Harley Wiltzer
PhD - McGill University
Co-supervisor :
Marc Gendron-Bellemare
Website
Github
Google Scholar
Hanna Yurchyk
Master's Research - McGill University
Github

Publications

Learning active tactile perception through belief-space control
Jean-François Tremblay
Johanna Hansen
David Meger
Francois Hogan
Gregory Dudek
Robot operating in an open world can encounter novel objects with unknown physical properties, such as mass, friction, or size. It is desira… (see more)ble to be able to sense those property through contact-rich interaction, before performing downstream tasks with the objects. We propose a method for autonomously learning active tactile perception policies, by learning a generative world model leveraging a differentiable bayesian filtering algorithm, and designing an information- gathering model predictive controller. We test the method on three simulated tasks: mass estimation, height estimation and toppling height estimation. Our method is able to discover policies which gather information about the desired property in an intuitive manner.
2022-05-12
ICRA.org/2022/Workshop/Contact-Rich (poster)
doi.org
openreview.net
Continuous MDP Homomorphisms and Homomorphic Policy Gradient
Sahand Rezaei-Shoshtari
Rosie Zhao
Prakash Panangaden
David Meger
Doina Precup
openreview.net
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
Scott Fujimoto
David Meger
Doina Precup
Marginalized importance sampling (MIS), which measures the density ratio between the state-action occupancy of a target policy and that of a… (see more) sampling distribution, is a promising approach for off-policy evaluation. However, current state-of-the-art MIS methods rely on complex optimization tricks and succeed mostly on simple toy problems. We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy. The successor representation can be trained through deep reinforcement learning methodology and decouples the reward optimization from the dynamics of the environment, making the resulting algorithm stable and applicable to high-dimensional domains. We evaluate the empirical performance of our approach on a variety of challenging Atari and MuJoCo environments.
2021-07-01
Proceedings of the 38th International Conference on Machine Learning (published)
proceedings.mlr.press
arxiv.org
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
Scott Fujimoto
David Meger
Doina Precup
Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-unifo… (see more)rm probability proportionate to their temporal-difference error. We show that any loss function evaluated with non-uniformly sampled data can be transformed into another uniformly sampled loss function with the same expected gradient. Surprisingly, we find in some environments PER can be replaced entirely by this new loss function without impact to empirical performance. Furthermore, this relationship suggests a new branch of improvements to PER by correcting its uniformly sampled loss function equivalent. We demonstrate the effectiveness of our proposed modifications to PER and the equivalent loss function in several MuJoCo and Atari environments.
arxiv.org