Group
The students, postdocs and staff I work with at Mila and the Université de Montréal.
Staff
- Anjelica KovacAdministrative assistant
- Anushree RankawatLab engineer
Postdoctoral researchers
- Borna Sayedana
- Gaspard LambrechtsWith Aditya Mahajan
- Wassim TenachiWith Yashar Hezaveh
PhD students
MSc students
- Arielle Gazzé
- Artiom Matvei
- Giorgi GamkrelidzeCo-supervised with Hanane Dagdougui
- Justin Veilleux
- Vamsi Krishna Munjuluri V S
Visiting researchers
- Mahdieh AdibFrom Concordia University
- Pablo BoitelFrom ÉTS
Alumni
Theses
- Tianwei (Victor) NiPhD 2026 History-Dependent Reinforcement Learning: Memory, Representation, and Adaptability
- Niki HowePhD 2026 Hackable, Attackable, and Unmonitorable: Failure Modes in Frontier Model Safety
- Parker LevesqueMSc 2025 Diffusion Models to Optimize Nonlinear Phase Reconstruction in Adaptive Optics SystemsCo-supervised with Yashar Hezaveh
- Pierluca D'OroPhD 2024 Building Intuitive Reinforcement Learning Algorithms
- Evgenii NikishinPhD 2024 Parameter, Experience, and Compute Efficient Deep Reinforcement Learning
- Julien RoyPhD 2024 Effective Reward Specification in Deep Reinforcement LearningCo-supervised with Chris Pal
- Vincent TabogaPhD 2024 On Intelligent and Adaptive Control of Thermal Loads in Buildings under Demand Response ProgramsCo-supervised with Hanane Dagdougui
- Léa Côté-TurcotteMSc 2024 Domain Adaptation in Reinforcement Learning via Causal Representation Learning
- Mahan FathiMSc 2024 Beyond the Horizon: Improved Long-range Sequence Modeling from Dynamical Systems to Language
- Sobhan MohammadpourMSc 2023 On Choice Models in the Context of MDPsCo-supervised with Emma Frejinger
- Padideh NouriMSc 2023 Sample Efficient Reinforcement Learning for Biological Sequence Design
- David Yu-Tung HuiMSc 2023 Stable Continuous ControlCo-supervised with Aaron Courville
- Paul CroutherMSc 2023 Model-Based Hyperparameter Optimization
- Anushree RankawatMSc 2023 Accelerated Algorithms for Temporal Difference Learning Methods
- Simon Dufort-LabbéMSc 2021 Steepest Descent as Linear Quadratic Regulation
- Niki HoweMSc 2021 Learning Neural Ordinary Differential Equations for Optimal Control
- Michel MaMSc 2021 Parsimonious Reasoning in Reinforcement Learning for Better Credit Assignment
Past collaborators and interns
- Adrien GoldszalIntern
- Claire BouilletIntern
- Esther DermanPostdoc
- Clement GehringPostdoc
- David Kanaa
- Samy RasmyIntern
- Dilip ArumugamIntern
- Romina AbachiIntern
- Lama SaoumaIntern
- Qizhen (Irene) ZhangIntern
- Victor ButoiIntern
- Ionelia BuzatuIntern
- Ryan D'OrazioCollaboration with Ioannis Mitliagkas
- Arushi JainCollaboration with Doina Precup