Advanced Artificial Intelligence and Games

 

Starts on 01/01/1970

Ends on 01/01/1970

Title

IDG5259 - Advanced Artificial Intelligence and Games

Lecturer

Konstantinos Makantasis, konstantinos.makantasis@um.edu.mt

Ahmed Abdelsamea Hassan Khalifa, ahmed.khalifa@um.edu.mt

Antonios Liapis, antonios.liapis@um.edu.mt

Georgios N. Yannakakis, georgios.yannakakis@um.edu.mt

Content and organization

The primary goal of the course is to revisit the field of game artificial intelligence (AI) and introduce non-traditional uses of AI in games. A short introduction will be given on AI areas that are currently reshaping the game AI research and development roadmap including procedural content generation, player experience modeling, and AI-based game design. The primary focus of the course will be on player modeling and procedural content generation. In player modeling, the course explores several different topics spanning from game analytics and game data mining to affective computing methods. In procedural content generation, the course explores all the various steps of generating a content starting from the different ways to represent the generated content to evaluating the content generator and visualize its outputs.

The course will cover the topics of player modeling (including model Input, Output, and modeling approaches) and procedural content generation (constructive, search-based and machine-learning approaches).

Study-Unit Aims:

– Introduction to the theory and implementation of player modeling and procedural content generation algorithms;
– Uses of artificial and computational intelligence for modeling users of games and for generating content;

Learning Outcomes:

1. Knowledge & Understanding:

By the end of the study-unit the student will be able to:

– Describe and theorize on the algorithms and domains covered in class;
– Identify tasks that can be tackled through player modeling and procedural content generation methods and select the appropriate method for the problem under investigation;
– Compare the performance of different methods and reflect on their suitability for a domain.

2. Skills:

By the end of the study-unit the student will be able to:

– Design and implement efficient data mining, affect recognition, procedural content generation, modeling and adaptation algorithms;
– Evaluate the algorithms in a commercial-standard application (e.g. game production);
– Work efficiently in groups and evaluate the algorithms in data derived from commercial-standard game productions.

Main Text/s and any supplementary readings:

– Yannakakis and Togelius, “Artificial Intelligence and Games”, Springer Nature, 2018.
– Shaker, Togelius, and Nelson, “Procedural Content Generation in Games”, Springer International Publishing, 2016.
– Short and Adams, “Procedural generation in game design”, CRC Press, 2017.
– Yu, “Spelunky”, Boss Fight Books, 2016.
– Karth and Smith. “WaveFunctionCollapse: Content Generation via Constraint Solving and Machine Learning”, IEEE Transactions on Games, 2021.
– Snodgrass and Ontanón, “Learning to Generate Video Game Maps using Markov Models”, IEEE Transactions on Computational Intelligence and AI in Games, 2016.

Various online articles and textbook chapters.

Level

05 - Postgraduate Modular Diploma or Degree Course

Course Type

Semester Course

ECTS

10

Marking Scheme

Presentation (10%) + Oral Examination (40%) + Report (50%)

Language

English

Modality (online/in person):

Hybrid

Notes

Pre-requisite Qualifications: Bachelor's in Engineering/CS or related fields; Object-oriented Programming

Host Institution
University of Malta

Other short courses

11. 05. 2022 Go

Geometric learning

05. 04. 2022 Go

Computer Graphics

04. 04. 2022 Go

Bayesian Learning

02. 04. 2022 Go

Computer Graphics

31. 03. 2022 Go

Web of Data

27. 03. 2022 Go

Machine Learning

02. 03. 2022 Go

Player Modeling

28. 02. 2022 Go

Player Modeling