News

The first class takes place Tuesday, January 8, 2019


General Information

Where: McConnell Engineering, room 304

When: Tuesday and Thursday, 2:35-3:55pm

What: The goal of this class is to provide an introduction to reinforcement learning, a very active part of machine learning. Reinforcement learning is concerned with building programs which learn how to predict and act in a stochastic environment, based on past experience. Applications of reinforcement learning range from classical control problems, such as powerplant 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 follow the second edition of the classic textbook by Sutton & Barto (available online), and supplement it as needed with papers and other materials.


Instructor

Doina Precup
School of Computer Science
Office: McConnell Engineering building, room 111N (left from elevators)
Office Hours: Tuesday and Thursday, 4:00-5:00pm Meetings at other times by appointment only
Phone: (514) 398-6443
E-mail: dprecup@cs.mcgill.ca


Teaching assistants

Riashat Islam
Office hours: Thursday 1-2pm, room TBD

Martin Klissarov
Office hours: Wednesday 1-2pm, room TBD

Sitao Luan
Office hours: Monday 2:30-3:30pm, room TBD

Harsh Satija
Office hours: Friday 5-6pm, room TBD

Srinivas Venkattaramanujan
Office hours: Friday 1:30-2:30pm, room TBD


References

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

MyCourses will be used only for bulletin board, discussion groups and assignment submission and grading.