Skip navigation
The Australian National University
Introduction to Artificial Intelligence COMP3620/COMP6320

Introduction to Artificial Intelligence COMP3620/COMP6320

Welcome to the AI course at the ANU !

The course covers a range of different topics within the field of AI, each taught by a specialist in that area. Introduction/Agents is taught by Peter Sunehag who is also the convenor and general contact person of the course, Search by Charles Gretton, Knowledge Representatoin and Reasoning by Scott Sanner, Planning by Patrik Haslum and Reinforcement Learning by Marcus Hutter. The main website for communication during the course is the wattle page.


Offered By: The AI Group @ Research School of Computer Science @ Australian National University
Offered In: First Semester, 2013
Lecturers: Peter Sunehag (Convenor), Charles Gretton, Scott Sanner, Patrik Haslum, Marcus Hutter
Tutors/Labs:Mayank Daswani, Ehsan Abbasnejad, Hadi Ashfar,Fazlul Hasan Siddiqui
Target: Undergraduate (COMP3620) and Graduate (COMP6320) students. Others welcome.
Enrollment: Undergraduates: The usual way via ISIS. Honors&Graduates&Others: Contact lecturer.
Admin: Bindi Mamouney and Kathy MacDonald
Unit Value: 6 units
Time Table: See Schedule below for details
Assessment: Assignments (50%); Exam (50%). Achieve at least 50% in total and 40% on both to pass. Textbook: Course textbook is "Artificial Intelligence - A Modern Approach", by Stuart Russell and Peter Norvig (Prentice Hall). This book gives a comprehensive tour of AI, and all of it is not part of the course material. Details about which chapters are included and additional course material will be given by the lecturers for each topic.
Study@ANU page:;details.html
Wattle page:
This page:

Prerequisites: Formally (as stated as studyat) COMP2100 or COMP2300 or COMP2500 or 2130 and COMP2600, but what you really need is a combination of basic abilities in mathematics and computer science. Contact the convenor (Peter Sunehag) if you do not meet the formal requirements but is still interested in taking the course.

Learning Outcomes

After completing this course, students should be able to:
  • Identify problems that are amenable to solution by AI methods, and which AI methods may be suited to solving a given problem.
  • Formalise a given problem in the language/framework of different AI methods (e.g., as a search problem, as a logical theory, as a planning problem, as an MDP, etc).
  • Implement basic AI algorithms (e.g., standard search algorithms or resolution).
  • Design and carry out an empirical evaluation of different algorithms on a problem formalisation, and state the conclusions that the evaluation supports.


There will be four assignments, one on search, on knowledge representation and reasoning (logic), one on planning and one on reinforcement learning. These make up half your final mark. The other half is the exam. The assignments are both rekleased and submitted through Wattle.


Assessment consists of four assignments and a final exam. The final mark is determined 50% by assignments, 50% by the exam. All four assignments have equal weight. Late assignments will be accepted, but subjected to a penalty of 20% (of maximal marks for the assignment) per day late. (That means assignments handed in five or more days after the deadline automatically have a mark of zero.) The minimum final mark required for a pass grade is 50% as usual. Note, however, that in order to obtain a passing grade, students must reach a minimum of 40% marks on both assignments and exam.


Week Lecture Tutorial/Lab
to be updated Tue 11-12, Thu 12-1, Fri 11-12 in Psyc G8
Tutorial in A:N108, B:Han2.25, C: CRISPG017, labs in A:N113,B:N112,C:N114
A:Thu 11-12,
B: Thu 1-2,
C: Fri 12-1
18Feb - 22Feb Introduction/Agents---
25Feb - 1Mar Searchtutorial
4Mar - 8Mar Search tutorial
11Mar - 15Mar Knowledge Representation and Reasoning lab
18Mar - 22Mar Knowledge Representation and Reasoning tutorial+assign 1 due
25Mar - 28Mar ... lab
29Mar - 12Apr break ---
15Apr - 19Apr Planning assign 2 due
22Apr - 26Apr Planning tutorial
29Apr - 3May Reinforcement Learning
6May-10May Reinforcement Learning tutorial+assignment 3 due
13May-17May Reserve+overview lectures lab
20May-24May assignment 4 due

Updated:  16 January 2014 / Responsible Officer:   JavaScript must be enabled to display this email address. / Page Contact:   JavaScript must be enabled to display this email address. / Powered by: Snorkel 1.4