Theorised best parent optimisation: an approach for playstyle creativity via preference-driven evolutionary content generation

Heaton, Padraic Gerald

Theorised best parent optimisation: an approach for playstyle creativity via preference-driven evolutionary content generation

Heaton, Padraic Gerald

Permalink

Publication Type:: Thesis
Issue Date:: 2024

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (27.84 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Heaton, Padraic Gerald
dc.date.accessioned	2025-05-26T23:45:51Z
dc.date.available	2025-05-26T23:45:51Z
dc.date.issued	2024
dc.identifier.uri	http://hdl.handle.net/10453/187519
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Genetic Algorithms rely on the discovery of the best population member to pass their genetic code onto the next generation; finding a perfect solution using this method requires large population numbers and many generations to evolve. This is important when adapting these types of algorithms into the context of an FPS. All input data comes from the player's interactions with each generated item, requiring the system to be able to function effectively without the player sorting through thousands of items; in essence, requiring a genetic algorithm to remain effective with smaller generation numbers and population sizes. This thesis proposes a solution to this problem through creating a theoretically ideal best parent in addition to relying on the best parents from each generation to be used in creating the next. This is an effective solution for this use case as it can bypass the need for multiple generations by estimating the player's preferred weapon loadout generations before that combination could appear naturally.	en_US.UTF-8
dc.format	Thesis (MSc(CompSc))
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/187519/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2024 Padraic Gerald Heaton
dc.rights	au.edu.uts.lib/cph
dc.title	Theorised best parent optimisation: an approach for playstyle creativity via preference-driven evolutionary content generation	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Genetic Algorithms rely on the discovery of the best population member to pass their genetic code onto the next generation; finding a perfect solution using this method requires large population numbers and many generations to evolve. This is important when adapting these types of algorithms into the context of an FPS. All input data comes from the player's interactions with each generated item, requiring the system to be able to function effectively without the player sorting through thousands of items; in essence, requiring a genetic algorithm to remain effective with smaller generation numbers and population sizes. This thesis proposes a solution to this problem through creating a theoretically ideal best parent in addition to relying on the best parents from each generation to be used in creating the next. This is an effective solution for this use case as it can bypass the need for multiple generations by estimating the player's preferred weapon loadout generations before that combination could appear naturally.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/187519