CS 8803-003 Special Topics: Reinforcement Learning

Course Creators and Instructors

Charles Isbell
Charles Isbell
Creator, Instructor
Michael Littman
Michael Littman

Course Developer


Chris Pryby

Course Developer


Through a combination of classic papers and more recent work, the course explores automated decision making from a computational perspective. It examines efficient algorithms, where they exist, for single agent and multiagent planning as well as approaches to learning near-optimal decisions from experience.  

Topics include Markov decision processes, stochastic and repeated games, partially observable Markov decision processes, and reinforcement learning. Of particular interest will be issues of generalization, exploration, and representation. Students will replicate a result in a published paper in the area.


  • Successful completion of CS 7641: Machine Learning is strongly recommended.
  • Students should be familiar with object-oriented programming, preferably Java.

Course Preview


Homework assignments will cumulatively count for 50% of the student's overall grade, and the final project will count for the remaining 50% of the overall grade.


Students will be evaluated by homework assignments and a final project.

Required Course Readings

There is no required textbook. Several papers will be given as reading assignments throughout the course. More details will be provided during the semester.  

Suggested readings include Reinforcement Learning by Sutton and Barto. You can find this reading available for free, here.

Minimum Technical Requirements

  • Browser and connection speed: An up-to-date version of Chrome or Firefox is strongly recommended. We also support Internet Explorer 9 and the desktop versions of Internet Explorer 10 and above (not the metro versions). 2+ Mbps recommended; at minimum 0.768 Mbps download speed
  • Operating system: - PC: Windows XP or higher with latest updates installed - Mac: OS X 10.6 or higher with latest updates installed - Linux: Any recent distribution that has the supported browsers installed

Other Info

Schedule Policies
  • Details for deadlines will be given with each assignment. No late work will be accepted unless warranted by extraordinary circumstances. There are few extraordinary circumstances.

The instructor and TA will moderate discussions on the course Piazza forum.

Academic Honesty

All Georgia Tech students are expected to uphold the Georgia Tech Academic Honor Code.