Generating procedural dungeons using machine learning methods: an approach with Unity-ML
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | eng |
Título da fonte: | Repositório Institucional da Universidade Federal Fluminense (RIUFF) |
Texto Completo: | https://app.uff.br/riuff/handle/1/22645 |
Resumo: | Procedural content generation (PCG) is a powerful tool to optimize creation of content in the game industry. However, it can lead to lack of control and mischaracterization of the game design, creating unbalanced or undesired situations. To overcome such problems, machine learning can be used to map important patterns of a game design and apply them in the PCG. Considering such aspects, this paper proposes a strategy for procedurally generating dungeons using ML techniques. We use Unity ML-Agents tool for the implementation, since dungeons are environments largely used in the industry that also require more control over its creation. The strategy used in this paper has proven to generate dungeons that respect room positioning design choices and maintains the game characterization. We conclude, after conducting a survey with users, that the generated dungeons presented reliable maps and showed to be more enjoyable and replayable than manually generated ones following the same design principles |
id |
UFF-2_9bc97d49113505b6b66b8c4f76006182 |
---|---|
oai_identifier_str |
oai:app.uff.br:1/22645 |
network_acronym_str |
UFF-2 |
network_name_str |
Repositório Institucional da Universidade Federal Fluminense (RIUFF) |
repository_id_str |
2120 |
spelling |
Generating procedural dungeons using machine learning methods: an approach with Unity-MLProcedural generationLachine learningDungeonsUnityMLVideogameAprendizado de máquinaGeração proceduralProcedural content generation (PCG) is a powerful tool to optimize creation of content in the game industry. However, it can lead to lack of control and mischaracterization of the game design, creating unbalanced or undesired situations. To overcome such problems, machine learning can be used to map important patterns of a game design and apply them in the PCG. Considering such aspects, this paper proposes a strategy for procedurally generating dungeons using ML techniques. We use Unity ML-Agents tool for the implementation, since dungeons are environments largely used in the industry that also require more control over its creation. The strategy used in this paper has proven to generate dungeons that respect room positioning design choices and maintains the game characterization. We conclude, after conducting a survey with users, that the generated dungeons presented reliable maps and showed to be more enjoyable and replayable than manually generated ones following the same design principlesClua, Esteban W. G.Kohwalter, Troy CostaMelo, Sidney AraujoLopes, Mariana Werneck Roque2021-07-16T11:27:48Z2021-07-16T11:27:48Z2020info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesisapplication/pdfLOPES, Mariana Werneck Roque. Generating procedural dungeons using machine learning methods: an approach with Unity-ML. 2020. 34f. Trabalho de Conclusão de Curso (Graduação em Ciência da Computação) - Universidade Federal Fluminense, Niterói, 2021.https://app.uff.br/riuff/handle/1/22645http://creativecommons.org/licenses/by-nc-nd/3.0/br/CC-BY-SAinfo:eu-repo/semantics/openAccessengreponame:Repositório Institucional da Universidade Federal Fluminense (RIUFF)instname:Universidade Federal Fluminense (UFF)instacron:UFF2021-09-16T17:07:44Zoai:app.uff.br:1/22645Repositório InstitucionalPUBhttps://app.uff.br/oai/requestriuff@id.uff.bropendoar:21202021-09-16T17:07:44Repositório Institucional da Universidade Federal Fluminense (RIUFF) - Universidade Federal Fluminense (UFF)false |
dc.title.none.fl_str_mv |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
title |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
spellingShingle |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML Lopes, Mariana Werneck Roque Procedural generation Lachine learning Dungeons UnityML Videogame Aprendizado de máquina Geração procedural |
title_short |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
title_full |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
title_fullStr |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
title_full_unstemmed |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
title_sort |
Generating procedural dungeons using machine learning methods: an approach with Unity-ML |
author |
Lopes, Mariana Werneck Roque |
author_facet |
Lopes, Mariana Werneck Roque |
author_role |
author |
dc.contributor.none.fl_str_mv |
Clua, Esteban W. G. Kohwalter, Troy Costa Melo, Sidney Araujo |
dc.contributor.author.fl_str_mv |
Lopes, Mariana Werneck Roque |
dc.subject.por.fl_str_mv |
Procedural generation Lachine learning Dungeons UnityML Videogame Aprendizado de máquina Geração procedural |
topic |
Procedural generation Lachine learning Dungeons UnityML Videogame Aprendizado de máquina Geração procedural |
description |
Procedural content generation (PCG) is a powerful tool to optimize creation of content in the game industry. However, it can lead to lack of control and mischaracterization of the game design, creating unbalanced or undesired situations. To overcome such problems, machine learning can be used to map important patterns of a game design and apply them in the PCG. Considering such aspects, this paper proposes a strategy for procedurally generating dungeons using ML techniques. We use Unity ML-Agents tool for the implementation, since dungeons are environments largely used in the industry that also require more control over its creation. The strategy used in this paper has proven to generate dungeons that respect room positioning design choices and maintains the game characterization. We conclude, after conducting a survey with users, that the generated dungeons presented reliable maps and showed to be more enjoyable and replayable than manually generated ones following the same design principles |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 2021-07-16T11:27:48Z 2021-07-16T11:27:48Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
LOPES, Mariana Werneck Roque. Generating procedural dungeons using machine learning methods: an approach with Unity-ML. 2020. 34f. Trabalho de Conclusão de Curso (Graduação em Ciência da Computação) - Universidade Federal Fluminense, Niterói, 2021. https://app.uff.br/riuff/handle/1/22645 |
identifier_str_mv |
LOPES, Mariana Werneck Roque. Generating procedural dungeons using machine learning methods: an approach with Unity-ML. 2020. 34f. Trabalho de Conclusão de Curso (Graduação em Ciência da Computação) - Universidade Federal Fluminense, Niterói, 2021. |
url |
https://app.uff.br/riuff/handle/1/22645 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/br/ CC-BY-SA info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/3.0/br/ CC-BY-SA |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da Universidade Federal Fluminense (RIUFF) instname:Universidade Federal Fluminense (UFF) instacron:UFF |
instname_str |
Universidade Federal Fluminense (UFF) |
instacron_str |
UFF |
institution |
UFF |
reponame_str |
Repositório Institucional da Universidade Federal Fluminense (RIUFF) |
collection |
Repositório Institucional da Universidade Federal Fluminense (RIUFF) |
repository.name.fl_str_mv |
Repositório Institucional da Universidade Federal Fluminense (RIUFF) - Universidade Federal Fluminense (UFF) |
repository.mail.fl_str_mv |
riuff@id.uff.br |
_version_ |
1807838868744962048 |