Teaching Assistant

Graduate Course, Université de Montréal, DIRO (Mila), 2026

Teaching assistant for IFT 6162 — Building Up RL: From Dynamics and Control to Learning, a graduate course taught by Professor Pierre-Luc Bacon that constructs reinforcement learning from first principles in dynamics, optimization, and control theory. The course covers controlled systems and state-space modeling, discrete-time optimal control, trajectory optimization and model predictive control, dynamic programming, approximate value methods, policy optimization and gradient estimation, and deep RL algorithms (DQN, DDPG, TD3, policy gradients).

  • Prepared and ran weekly tutorial sessions, programming exercises, and problem sets
  • Held office hours and answered student questions on the course forum
  • Graded assignments and provided feedback on student projects