CS 392 - Game AI

Course Information

Course Overview

The objective of this course is to give each student a taste of research in computer science. There will be three 4-5 week projects involving search and machine-learning techniques.  Each problem will be a challenging, "open" research problem.  The three project are as follows:

Each project will consist of these phases:

As this is a project course, a student would ideally:


Machine Learning, Tom Mitchell, McGraw Hill, 1997. 
ISBN 0070428077 
Stuart J. Russell, Peter Norvig
Artificial Intelligence: A Modern Approach
Prentice Hall; ISBN: 0131038052

The Russell & Norvig text was used in CS 371 (Artificial Intelligence) and will be used for coverage of basic search concepts.  This text is not officially required for this course because (1) We'll only spend the first couple weeks with the search material, and (2) students should be able to borrow this text from previous AI students or find it on reserve in the library.  If this poses too much inconvenience, you can order the book easily through Amazon.com.

The Machine Learning text is expensive and relevant to the second and third projects.  A copy will also be on reserve in the library.

Beyond the context of this course, I'd recommend the Russell & Norvig book for a general AI introduction, and I'd recommend the Mitchell book for its coverage of AI maching learning material.


Todd Neller
M,W,F 1:10PM
Office: Glatfelter 209
Office Hours: M,W,F 10:00-10:45AM; Tu, Th 1:10-2:00PM or by appointment. Note:  Generally, feel free to drop in if my office door is open.  If it is closed, I'm desperately seeking to keep on top of things and rabid attack ferrets may drop from the ceiling in my defense.
Phone: 337-6643


90% Projects (3 projects, each made up of multiple component)
10% Class Attendance/Participation

This course will be run very much like an independent research course.  A subset of the lectures times will be used to present material relevant to 3 major research projects.  Beyond the lectures, expect to report approximately weekly on progress.  Research is often a self-motivated venture.  Although I will provide guidance for when you should complete various stages, you must find within yourself the desire and discipline for success in this endeavor.  Accordingly, "due dates" may be individualized.

Class attendance and participation is required unless (1) you have taken the lecture topic in CS 371, and (2) you're sure that nothing beyond the topic will be covered or discussed.  The class attendance and participation portion of your grade will therefore reflect your attendance for lectures with new material and/or class discussion, and your punctuality for scheduled status report meetings.

Honor Code

Honesty, Integrity, Honor.  These are more important than anything we will teach in this class.  Since you will be encouraged to work in groups, the most important application of the honor code is that you represent the extent of your project contributions accurately.  For detailed information about the honor code, see