Back to search

Institutional Repository of Vilnius University

Automatinis žaidimų lygių generavimas naudojant dirbtinį intelektą /

Abstract

dc:description

This work explores how modern artificial intelligence techniques can be applied to automate the generation of 2D platform levels in the Unity engine, while at the same time ensuring playfulness and design quality. Three generation methods are implemented and compared: ● Generative Adversarial Networks (GANs), trained on manually generated level datasets; ● Markov chains using tile transition probabilities; ● Wave Function Collapse (WFC), a constraint-based algorithm inspired by pixel pattern synthesis. The generated levels are evaluated using various quality criteria such as playfulness, diversity, complexity and aesthetics. The levels are visualised and analysed in Unity using C# scripts, and Unity Sentis is used to infer the conclusions of the trained neural models in real time. The aim of this thesis is to identify the most suitable method for generating levels for a 2D platform game.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Paškevič, Rafal,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Paškevič, Rafal,. Automatinis žaidimų lygių generavimas naudojant dirbtinį intelektą /. Institutional Repository of Vilnius University, 2025. https://repository.vu.lt/VU:ELABAETD239024987&prefLang=en_US