Department of Electrical Engineering & Computer Science
ECE 517: Reinforcement Learning in Artificial Intelligence
Course Homepage: ECE-517
Lectures: T/TR 11:10 – 12:25 PM (MK 405)
Instructor: Dr. Itamar Arel
Office: MK 608
Office Hours: T/Tr 2:00PM – 3:00PM
TA: Aaron Mishtal – Office located in MK 606
Office hours: MWF: 12:00 – 2:00pm
Reinforcement learning (RL) is an exciting and relatively new machine learning discipline, which corresponds to a broad class of methods that allow a system to learn how to behave in environments that are incompletely known/specified based on reward signals. A key concept in RL is that the intelligent agent learns autonomously, based on acquired experience, rather than by being externally instructed or supervised. This course will address various topics pertaining to the theory and practice of RL.
Background in linear algebra and probability theory, as well as knowledge of the Matlab© programming, are required.
Lecture notes will be posted and made available at the course website. The majority of the material will appear in the lecture notes and supplemental reading material (papers). The course textbook will be:
m R. Sutton and A. Barto, “Reinforcement Learning: An Introduction,” 2015, 2nd Ed. (available online at: http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html)
The course will include two small projects and a final project. The final project will also involve an in-class presentation by the students.
There will be five assignment sets issued. Students are expected to complete all of the assigned problems. Assignment sets are to be submitted at the beginning of the class in which they are due.
There will be one in-class midterm exam. No make-up exams will be offered.
The following topics will be covered:
q Foundations of machine learning & autonomous cognitive systems
q Markov decision processes (MDP)
q Neural networks
q Dynamic programming
q Temporal difference (TD) learning
q Monte Carlo reinforcement learning methods
q Eligibility traces
q Hardware & software implementation considerations
q Deep Reinforcement Learning
Final Grade A 90 – 100 B+ 87 – 89 B 80 – 86 C+ 77 – 79 C 70 – 76 D 60 – 69 F 0 – 59
90 – 100
87 – 89
80 – 86
77 – 79
70 – 76
60 – 69
0 – 59
Small projects (2 × 12.5 points) = 25%
Assignment sets (5 × 5 points) = 25%
Midterm exam = 20%
Final project = 30%
Students are encouraged to frequently visit the course website for announcements and updates.