CS3S667 - Artificial Intelligence for Game Developers 01 Jul 2022 - 31 Aug 2028 | Version 3

Associated Module Information

Module Code: CS3S667
Module Title: Artificial Intelligence for Game Developers
Faculty: Faculty of Computing, Engineering and Science
Faculty Group: Computing and Mathematical Sciences
Faculty Sub Group: Computer Science
Module Leader: Mike Reddy
Module Team: Christopher Tubb
First Intended Intake: SEP 2017 Final Year of Intake:
Date Closed:
Credit Value: 20 Credit Level: 6
Language: English
Percentage of Module Taught in Welsh: 0
Equivalent Module:
HECOS codes: 101020 - computer games programming
HECOS Code Weighting: 100

Document Version Information

Version 3
Valid From 01 Jul 2022
Valid To 31 Aug 2028

Module Aims

To appraise the students of the importance of artificial intelligence within today’s game industry

To develop the skills necessary to apply and integrate cutting-edge AI with more established AI techniques in modern games

Content Summary

Introduction to Game AI: controlling entities in games

Movement Algorithms: steering behaviors, path-finding, flocking , grid traversal, search algorithms and cooperative AI

Decision Making: decision trees, state machines, fuzzy logic, goal-oriented behaviour, rule-based systems, scripting, Markov systems

Tactical and Strategic AI: waypoint networks, tactical analyses, coordinated action

Machine Learning: action prediction, reinforcement learning, artificial neural networks and case based reasoning, Genetic Algorithms

AI Engine Integration

Learning and Teaching Methods

Activity Type Hours
Lecture 24
Practical classes and workshops 24
Independent Study 80
Directed Study 72
Total Hours Selected 200

Learning Outcomes

# Learning Outcome
LO1 Understand the theory that underpins, and the pragmatic difficulties associated with, the development of a working AI game system
LO2 Evaluate the relative effectiveness of different approaches to AI for a given problem

Module Requisites

N/A

Assessment Criteria

Assessment Category Assessment Type Description Duration Word Count Weight (%) Best of? Pass Mark
Asynchronous Assessment Practical Coursework 2 (Asynch) Apply knowledge to the solution of a machine learning problem and report on findings 0 3000 50 No 40
Asynchronous Assessment Practical Coursework 1 (Asynch) Apply knowledge to the solution of a navigation/planning problem and report on findings 0 3000 50 No 40

Assessment Matrix

Assessment Type Learning Outcomes
LO1 LO2
Practical Coursework 2 (Asynch)
Practical Coursework 1 (Asynch)

Reading List