What is this class about?

Artificial Intelligence (AI) has become a household name. Are you interested to understand what’s under the hood of AI technology? Are you interested to know how to use these AI technology beyond mere black-box? This class aims to help you gain those skills for a particular sub-field of AI, namely decision-making under uncertainty in robotics.

Robots have the potential to make society safer and more efficient, from reducing the need for humans to perform dangerous jobs to enhancing services in remote areas to helping busy parents with everyday chores. However, their wide-spread use have often been hindered by the ubiquity of uncertainty. In this class, we will explore and discuss some of the concepts, approaches, and tehniques that would enable robots to embrace and work with uncertainty, rather than avoiding them.

In this class, we will view robots in a broad sense of intelligent agents that operate in the physical or simulated physical world and will discuss concepts, basic approaches, recent scalable approaches of:

  • Planning in continuous and hybrid spaces (in contrast to the discrete space planning in COMP3620/6320)
  • Decision-making when the effects of actions are uncertain (i.e., Markov Decision Processes)
  • Decision-making when the effects of actions are uncertain and the world is only partially observable (i.e., Partially Observable Markov Decision Processes)
  • Decision-making when models are unavailable a priori (i.e., Reinforcement Learning and integrated planning and learning)

Although we will focus on robotics applications, many of the approaches we will discuss are general and can be applied to various domain and occasionally, if time permits, we will discuss applications in other domains, such as in cyber domain.


To help you learn, this class consists of a 2 hour lecture and 2 hour tutorial/lab per week.

Lectures will start from week-1 and will be on Tuesday 11am-1pm AEST in building 39 (Psychology building) Room G06.

Tutorials will start from week-2. Please select one of the following tutorial slots in mytimetable before 1 Aug’23 23:59.

  • Thursday 2pm-4pm AEST in CSIT N115/116
  • Friday 3pm-5pm AEST in CSIT N115/116

The class forum will be in this Piazza forum. All announcement for this class will be in the class’ Piazza forum.

Class schedule

All materials (slides, reading, assignments, etc.) will be available in the wattle page of this class.

A tentative schedule of the topics covered is in the Schedule page.


The assessments in this class will be more open ended that 3000 level courses.

The assessments consist of 2 assignments and 1 final assessment.

  • Each assignment will include problem solving question(s) and involve concept understanding, application and implementation of the concepts using high level programming language, design of systematic experiments in simulation, analysis of the results, and technical report writing. The first assignment will be worth 25%, while the second 30%.
  • The final assessment will be a mini-research project that includes an in-person exam. It will involve critically reviewing paper(s), understanding of the concepts taught in the class, applying and potentially expanding the concepts to solve problems, and articulating the solution. Although the exam will be individual, all other parts of the project will be conducted in a group of 2-3 students. The final assessment will be worth a total of 45%, with the exam worth 20% and other parts of the project worth a total of 25%.

Assumed background

Since this is a fourth-year / Master course in Computing, we will assume that students have the following background:

  • Basic mathematics
  • Good programming skills using high-level programming language (e.g., Python / C++)
  • Knowledge of Introductory AI materials (e.g., has taken COMP3620/6320).


Convenor & lecturer: Hanna Kurniawati


  • Ivan Ang
  • Jingyang You
  • Ruijia Zhou
  • Yohan Karunanayake
  • Yuxin Cao
bars search times arrow-up