Back to search

Institutional Repository of Vilnius University

Procedural generation of game levels /

Abstract

dc:description

A game already released, Spelunky, was taken, and its procedural generation method was analyzed and improved. The goal of the improvement is to create more unique and varied levels. It was also made sure that the generation was quick enough that it could run in the runtime of the game in-between game levels, like the current generation does in Spelunky. It was important not to introduce any significant downsides that usually come with making procedural generation more random. To accomplish this, a complex algorithm that uses machine learning was simplified without losing the benefits it provides. A technique of evaluating every generated level difficulty introduced the ability not only to create levels, but also to choose levels according to how hard they are.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zolba, Gustas,

Subjects

dc:subject × 1

Rights

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

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
citation

Zolba, Gustas,. Procedural generation of game levels /. Institutional Repository of Vilnius University, 2023. https://repository.vu.lt/VU:ELABAETD192833030&prefLang=en_US