The Department
of Electrical Engineering & Computer Science ECE
517: Reinforcement Learning in Artificial Intelligence Fall
2015 Course Homepage: ECE517 

General Information Lectures: T/TR
11:10 – 12:25 PM (MK 405) Instructor: Dr.
Itamar Arel Email: itamar@eecs.utk.edu Office: MK
608 Office Hours: T/Tr 2:00PM – 3:00PM Tel: (865)9743891 TA: Aaron
Mishtal – Office located in MK 606 Office
hours: MWF: 12:00 – 2:00pm
email: amishtal@utk.edu 

Course Description 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.


Prerequisites Background in linear algebra and probability theory, as well as knowledge of the Matlab©
programming, are required. 

Reference Material 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, 2^{nd}
Ed. (available online at: http://webdocs.cs.ualberta.ca/~sutton/book/thebook.html) 

Projects The course will include two small projects and a final project. The final project will also involve an inclass presentation by the students. 

Assignment Sets 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
inclass midterm exam. No makeup exams will be offered. 

Syllabus 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 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. 

