Portrait de Antoine Lesage-Landry

Antoine Lesage-Landry

Membre académique associé

Professeur agrégé, Polytechnique Montréal, Département de génie électrique

Sujets de recherche

Apprentissage en ligne

Optimisation

Biographie

Je suis professeur agrégé au Département de génie électrique de Polytechnique Montréal. J’ai obtenu un baccalauréat en génie physique de Polytechnique Montréal en 2015 et un doctorat en génie électrique de l’Université de Toronto en 2019. Avant de me joindre à Polytechnique Montréal, j’ai été chercheur postdoctoral au Energy & Resources Group de l’Université de la Californie à Berkeley de 2019 à 2020. Mes champs d’intérêt en recherche incluent l’optimisation, l’apprentissage en ligne et l’apprentissage automatique ainsi que leurs applications aux réseaux électriques utilisant de l’énergie renouvelable.

Étudiants actuels

Maîtrise recherche - Polytechnique

Maîtrise recherche - Polytechnique

Olivier Bélanger

Maîtrise recherche - Polytechnique

Mohamed Charara

Maîtrise recherche - Polytechnique

Co-superviseur⋅e :

Hanane Dagdougui

Marc-Antoine Coulombe

Doctorat - Université du Québec à Rimouski

Victor Darleguy

Maîtrise recherche - Polytechnique

Maîtrise recherche - Polytechnique

Maîtrise recherche - Polytechnique

Jérôme Lafontaine

Maîtrise recherche - Polytechnique

Doctorat - Polytechnique

Maîtrise recherche - Polytechnique

Doctorat - Polytechnique

Maîtrise recherche - Polytechnique

Christina G. Soldati

Maîtrise recherche - Polytechnique

Etienne Tremblay

Maîtrise recherche - Polytechnique

Doctorat - Polytechnique

chao.yin@polymtl.ca

Maîtrise recherche - Polytechnique

Baptiste ZOGHBY

Stagiaire de recherche - Polytechnique

Publications

Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads

Vincent Mai

Philippe Maisonneuve

Tianyu Zhang

Hadi Nekoei

Antoine Lesage-Landry

To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale var… (voir plus)iations in power generation. Frequency regulation through demand response has the potential to coordinate temporally flexible loads, such as air conditioners, to counteract these variations. Existing approaches for discrete control with dynamic constraints struggle to provide satisfactory performance for fast timescale action selection with hundreds of agents. We propose a decentralized agent trained with multi-agent proximal policy optimization with localized communication. We explore two communication frameworks: hand-engineered, or learned through targeted multi-agent communication. The resulting policies perform well and robustly for frequency regulation, and scale seamlessly to arbitrary numbers of houses for constant processing times.

2023-01-01

AAMAS (publié)

An Online Newton’s Method for Time-Varying Linear Equality Constraints

Jean-Luc Lupien

Antoine Lesage-Landry

We consider online optimization problems with time-varying linear equality constraints. In this framework, an agent makes sequential decisio… (voir plus)ns using only prior information. At every round, the agent suffers an environment-determined loss and must satisfy time-varying constraints. Both the loss functions and the constraints can be chosen adversarially. We propose the Online Projected Equality-constrained Newton Method (OPEN-M) to tackle this family of problems. We obtain sublinear dynamic regret and constraint violation bounds for OPEN-M under mild conditions. Namely, smoothness of the loss function and boundedness of the inverse Hessian at the optimum are required, but not convexity. Finally, we show OPEN-M outperforms state-of-the-art online constrained optimization algorithms in a numerical network flow application.

2023-01-01

IEEE Control Systems Letters (publié)