PA217 Artificial Intelligence for Computer Games

Faculty of Informatics
Spring 2025
Extent and Intensity
2/0/0. 2 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium).
In-person direct teaching
Teacher(s)
doc. Mgr. Hana Rudová, Ph.D. (lecturer)
RNDr. Vojtěch Brůža (assistant)
Bc. Vladimír Žbánek (assistant)
Guaranteed by
doc. Mgr. Hana Rudová, Ph.D.
Department of Machine Learning and Data Processing – Faculty of Informatics
Supplier department: Department of Machine Learning and Data Processing – Faculty of Informatics
Prerequisites
PV255 Game Development I || SOUHLAS
For completion as an examination, the base knowledge of Unity is required. If PV255 is not successfully passed, the student must demonstrate a representative set of projects solved in Unity. Based on that, course enrollment is confirmed or not. The projects should be sent to the teacher by the beginning of the semester (or in the first week of the semester).
For completion as a colloquium, the prerequisite of PV255 is not required for the course enrollment (agreement is guaranteed).
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
Course objectives
The course provides information about methods of artificial intelligence used for the development of computer games. Students will learn about data structures and algorithms from artificial intelligence needed for movement, pathfinding, decision making for a single character, strategy, and tactics. Students passing the course using the examination will have practical experience with AI programming.
Learning outcomes
The graduate will be able to apply artificial intelligence algorithms and approaches in computer games.
The graduate will learn how to propose and implement the movement of AI characters in games.
The graduate will learn the basics of search algorithms, how to represent worlds in games, and how to process and implement path planning in games.
The graduate will understand principles and approaches for the decision making of a single AI character and will be aware of the principles and ideas behind strategic and tactical behaviors for groups of AI characters.
The graduate will learn what the base algorithms behind board games are.
When passing the course using the examination, the graduate will know how to implement artificial intelligence algorithms in the game engine by coding in Unity.
Syllabus
  • Introduction and history.
  • Movement: kinematic movement, steering behaviors, combining steering behaviors.
  • Search and pathfinding: introduction to search algorithms, A* data structures and heuristics, world representation, hierarchical pathfinding.
  • Decision making for a single character: decision trees, state machines, behavior trees, fuzzy logic, Markov systems, goal-oriented behavior, rule-based systems, blackboard architectures, action execution.
  • Strategy and tactics: tactical waypoints, tactical analyses, tactical pathfinding, coordinated action.
  • Board games: minimaxing, transposition tables, Monte Carlo search.
  • Implementation of AI algorithms in Unity.
Literature
  • Millington, I. Artificial intelligence for games. CRC Press, 3rd edition, 2019.
  • Unity artificial intelligence programming. Edited by Davide Aversa. Fifth edition. Birmingham, UK: Packt Publishing, 2022, 1 online. ISBN 1803238534. URL info
  • Yannakakis, G. N., Togelius, J., Artificial Intelligence and Games. Springer, 2018.
  • Buckland, M., Programming Game AI by Example, Jones & Bartlett Learning, 2004.
Teaching methods
Standard lecture, no drills. Three homeworks including AI programming in Unity (when passing the course using the examination). Activity in lectures is encouraged by getting bonus points.
Assessment methods
When passing the course using an examination, the evaluation is given as a sum of points for homeworks, the final exam, and bonus points for activities at lectures: A more than 90, B 89-80, C 79-70, D 69-60, E 59-55.
It is possible to get up to 70 points for the final written exam; it is obligatory to get at least 40 out of 70 points.
There are three homeworks during the semester. Each student is required to obtain 16 points, at least from the total point of 30 points.
Also, each student can get 1 bonus point for activity in each lecture (1 point: student response to several easy questions and/or student questions to clarify some part of the lecture, student response to one harder question), i.e., it is possible to about 12 bonus points for activity based on the number of lectures.
When passing the course using a colloquium, it is required to get at least 40 out of 70 points from the final written exam (there are no other requirements).
Language of instruction
English
Further Comments
The course is taught annually.
The course is taught: every week.
Teacher's information
https://is.muni.cz/el/fi/jaro2024/PA217/index.qwarp
The course is also listed under the following terms Spring 2020, Spring 2021, Spring 2022, Spring 2023, Spring 2024.
  • Enrolment Statistics (recent)
  • Permalink: https://is.muni.cz/course/fi/spring2025/PA217