Reinforcement Learning and Optimal Control

This course (IFT6760C) is intended for advanced graduate students with a good background in machine learning, mathematics, operations research or statistics. You can register to IFT6760C on Synchro if your affiliation is with UdeM, or via the CREPUQ if you are from another institution. Due to the research-oriented nature of this class, you need to be comfortable with a teaching format involving open-ended questions and assignments. You will be required to think critically and adopt an open mindset. My teaching goal with this course is for all the participants to build their own understanding of reinforcement learning in relation to their primary research area while sharing their unique perspective and insights with the entire class.

Evaluation

The following evaluation structure is subject to change depending on the class size.

• Assignments: 3 x 20% = 60%
• Final project: 40%

Recommended Textbooks

There is no mandatory textbook. I will however be referencing content from:

• Markov Decision Processes: Discrete Stochastic Dynamic Programming by Martin Puterman
• Reinforcement Learning and Optimal Control by Dimitri Bertsekas
• Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto
• Practical Methods for Optimal Control and Estimation Using Nonlinear Programming by John T. Betts
• Simulation and the Monte Carlo Method, Second Edition by Rubinstein and Kroese (2008)

Schedule

See IFT6760C-H20 for previous edition

Wellbeing

Academic life can sometimes be overwhelming. Don't hesitate to find support:

• UdeM: Centre de santé et de consultation psychologique
• McGill: Student wellness hub
• Polytechnique: Soutien à la réussite
• HEC: Psychological support and ressources