News

The course starts on Monday, January 6th. The lectures are also broadcast and recorded via zoom (on a best effort basis, no guarantees), but questions are only taken in person. The recordings (if there are no issues) are available in MyCourses.


General Information

When: Monday and Wednesday, 4:05-5:25pm

Where: Macdonald-Harrington G-10

What: The goal of this class is to provide an introduction to reinforcement learning, a very active sub-field of machine learning. Reinforcement learning is concerned with building computer agents that learn how to predict and act in a stochastic, dynamic environment, based on past experience. Applications of reinforcement learning range from classical control problems, such as power plant optimization or dynamical system control, to game playing, inventory control, and many other fields. Notably, reinforcement learning has also produced very compelling models of animal and human learning. During this course, we will study theoretical properties and practical applications of reinforcement leanring. We will start by following the second edition of the classic textbook by Sutton & Barto (available online), but we will supplement it with papers and other materials.


Instructors

Doina Precup

Isabeau Prémont-Schwarz


Teaching assistants

Shuyuan Zhang

Ali Saheb Pasand

Zihan Wang

Valliappan Chidambaram Adaikkappan

Farnoosh Faraji


References

Required textbook: Lecture notes and other relevant materials are linked to the schedule web page.

MyCourses will be used for bulletin board, access to Ed, assignment submission and grading.