Units / FIT3203
FIT3203 · Intelligent agents
2026 Handbook6 credit pointsLevel 3Faculty of Information Technology
Last checked: 23 Aug 2026 UTCOverview
This unit introduces you to the field of Artificial Intelligence (AI) as a specialisation within Computer Science. It provides an overview of the foundations of AI, including the history, key concepts, and applications across diverse domains such as language, vision, and intelligent decision-making. You will explore introductory AI problem-solving techniques and develop a basic understanding of how AI systems are designed to emulate aspects of intelligence. In parallel, the unit equips you with the essential mathematical and computational foundations required for later AI units. These include fundamental concepts from linear algebra and vector calculus, introduced in the context of solving simple AI-related problems such as classification and optimisation. Practical labs emphasise hands-on engagement through simulations, mathematical reasoning, and basic AI model-building, along with reflection on the societal and ethical implications of AI technologies.
Offerings
The Handbook publishes no offerings for this unit.
Assessment
The Handbook does not list a final examination among the assessment items. That is not a guarantee there is none.
| # | Assessment | Type | Weight | Hurdle |
|---|---|---|---|---|
| 1 | Assessment Task 1: Reinforcement Learning Agent | Artefact | 30% | — |
| 2 | Assessment Task 2: Multi-Agent Pathfinding | Artefact | 20% | — |
| 3 | Assessment Task 3: Game Theory and Agent Decision-Making | Written | 50% | — |
Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.
Requisites
Learning outcomes
- Explain the characteristics and architectures of intelligent agents, planning and automated reasoning.
- Compare model-based and model-free reinforcement learning.
- Construct intelligent agents to achieve defined goals efficiently
- Build simulations under which emergent large-scale phenomena appear as a result of local agent-level interactions.
- Evaluate the performance and limitations of intelligent agent systems in practical applications.
Workload
Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities.
| Activity | Duration |
|---|---|
| Workshops | 24 hours |
| Applied sessions | 22 hours |
Ask about FIT3203
Answered from the Handbook fields above — no AI, no guessing. Every answer links back to the source.
Community discussions about FIT3203
CommunityStudent experience, not official rules. Nothing here changes what the Handbook says.