Portrait de Pierre-Luc Bacon

Pierre-Luc Bacon

Membre académique principal
pierre-luc.bacon@mila.quebec
Chaire en IA Canada-CIFAR
Professeur adjoint, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Apprentissage par renforcement
Site web
Google Scholar

Biographie

Pierre-Luc Bacon est professeur agrégé au Département d'informatique et de recherche opérationnelle de l'Université de Montréal. Il est également membre de Mila – Institut québécois d’intelligence artificielle et d’IVADO et titulaire d'une chaire Facebook-CIFAR. Il dirige un groupe de recherche qui travaille sur le défi posé par la malédiction de l'horizon dans l'apprentissage par renforcement et le contrôle optimal.

Étudiants actuels

Claire Bouillet
Stagiaire de recherche - UdeM
Github
Diego Calanzone
Doctorat - UdeM
Site web
Github
Google Scholar
Pierluca D'Oro
Collaborateur·rice alumni - UdeM
Co-superviseur⋅e :
Marc Gendron-Bellemare
Site web
Github
Google Scholar
Esther Derman
Postdoctorat - UdeM
Co-superviseur⋅e :
Erick Delage
Site web
Github
Google Scholar
Simon Dufort-Labbé
Doctorat - UdeM
Giorgi Gamkrelidze
Maîtrise recherche - Polytechnique
Superviseur⋅e principal⋅e :
Hanane Dagdougui
Arielle Gazzé
Maîtrise recherche - UdeM
Clement Gehring
Collaborateur·rice alumni - UdeM
Adrien Goldszal
Stagiaire de recherche - UdeM
adrien.goldszal@polytechnique.edu
Niki Howe
Doctorat - UdeM
Site web
Github
Google Scholar
Parker Levesque
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e :
Yashar Hezaveh
Github
Lu Li
Doctorat - UdeM
Github
Google Scholar
Michel Ma
Doctorat - UdeM
Github
Google Scholar
Artiom Matvei
Maîtrise recherche - UdeM
Aneri Muni
Doctorat - UdeM
Vamsi Krishna Munjuluri V S
Maîtrise recherche - UdeM
mvkrishna2001@gmail.com
Tianwei Ni
Doctorat - UdeM
Site web
Github
Google Scholar
Evgenii Nikishin
Doctorat - UdeM
Co-superviseur⋅e :
Aaron Courville
Site web
Github
Google Scholar
Anushree Rankawat
Doctorat - UdeM
Yihao Sun
Doctorat - UdeM
Site web
Github
Google Scholar
Wassim Tenachi
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Yashar Hezaveh
Github
Google Scholar
Justin Veilleux
Maîtrise recherche - UdeM

Publications

Continuous-Time Meta-Learning with Forward Mode Differentiation
Tristan Deleu
David Kanaa
Leo Feng
Giancarlo Kerg
Yoshua Bengio
Guillaume Lajoie
Pierre-Luc Bacon
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learni… (voir plus)ng (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.
2022-01-28
ICLR.cc/2022/Conference (spotlight)
doi.org
openreview.net
Options of Interest: Temporal Abstraction with Interest Functions
Khimya Khetarpal
Martin Klissarov
Maxime Chevalier-Boisvert
Pierre-Luc Bacon
Doina Precup
Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. Th… (voir plus)e options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.
2020-04-03
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Policy Evaluation Networks
Jean Harb
Tom Schaul
Doina Precup
Pierre-Luc Bacon
2020-02-26
ArXiv (prépublication)
arxiv.org
arxiv.org