World-GAN: A Generative Model for Minecraft Worlds

Maren Awiszus; Frederik Schubert; Bodo Rosenhahn

doi:10.48550/arXiv.2106.10155

World-GAN: A Generative Model for Minecraft Worlds

Maren Awiszus^*, Frederik Schubert^*, Bodo Rosenhahn^*

^*Korrespondierende*r Autor*in für diese Arbeit

Institut für Informationsverarbeitung

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Abstract

This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.

Originalsprache	Englisch
Titel des Sammelwerks	2021 IEEE Conference on Games, CoG 2021
Herausgeber (Verlag)	IEEE Computer Society
ISBN (elektronisch)	9781665438865
ISBN (Print)	978-1-6654-4608-2
DOIs	https://doi.org/10.48550/arXiv.2106.10155 https://doi.org/10.1109/CoG52621.2021.9619133
Publikationsstatus	Veröffentlicht - 2021
Veranstaltung	2021 IEEE Conference on Games, CoG 2021 - Copenhagen, Dänemark Dauer: 17 Aug. 2021 → 20 Aug. 2021

Publikationsreihe

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
Band	2021-August
ISSN (Print)	2325-4270
ISSN (elektronisch)	2325-4289

Konferenz

Konferenz	2021 IEEE Conference on Games, CoG 2021
Land/Gebiet	Dänemark
Ort	Copenhagen
Zeitraum	17 Aug. 2021 → 20 Aug. 2021

ASJC Scopus Sachgebiete

Artificial intelligence
Computergrafik und computergestütztes Design
Maschinelles Sehen und Mustererkennung
Mensch-Maschine-Interaktion
Software

Zugriff auf Dokument

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

PhoenixD: Exzellenzcluster 2122/1: Photonics, Optics, and Engineering – Innovation Across Disciplines
Morgner, U. (Projektleiter*in (Principal Investigator)) & Overmeyer, L. (Leitende*r Forscher*in (Co-Principal Investigator))
1 Jan. 2019 → 31 Dez. 2025
Projekt: Forschung

Dieses zitieren

@inproceedings{6105712ca468446e8336335318d48a5c,

title = "World-GAN: A Generative Model for Minecraft Worlds",

abstract = "This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.",

keywords = "GAN, Generation, Level, Minecraft, PCG, Representation, Scales, Sin-GAN, Single Example, Style",

author = "Maren Awiszus and Frederik Schubert and Bodo Rosenhahn",

note = "Funding Information: VI. ACKNOWLEDGMENT This work has been supported by the Federal Ministry of Education and Research (BMBF), Germany, under the project LeibnizKILabor (grant no. 01DD20003), the Federal Ministry for Economic Affairs and Energy under the Wipano programme ”NaturalAI” (03THW05K06), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungsgemein-schaft (DFG) under Germany{\textquoteright}s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122). Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Conference on Games, CoG 2021 ; Conference date: 17-08-2021 Through 20-08-2021",

year = "2021",

doi = "10.48550/arXiv.2106.10155",

language = "English",

isbn = "978-1-6654-4608-2",

series = "IEEE Conference on Computatonal Intelligence and Games, CIG",

publisher = "IEEE Computer Society",

booktitle = "2021 IEEE Conference on Games, CoG 2021",

address = "United States",

}

Awiszus, M, Schubert, F & Rosenhahn, B 2021, World-GAN: A Generative Model for Minecraft Worlds. in 2021 IEEE Conference on Games, CoG 2021., 175285, IEEE Conference on Computatonal Intelligence and Games, CIG, Bd. 2021-August, IEEE Computer Society, 2021 IEEE Conference on Games, CoG 2021, Copenhagen, Dänemark, 17 Aug. 2021. https://doi.org/10.48550/arXiv.2106.10155, https://doi.org/10.1109/CoG52621.2021.9619133

World-GAN: A Generative Model for Minecraft Worlds. / Awiszus, Maren; Schubert, Frederik; Rosenhahn, Bodo.
2021 IEEE Conference on Games, CoG 2021. IEEE Computer Society, 2021. 175285 (IEEE Conference on Computatonal Intelligence and Games, CIG; Band 2021-August).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

TY - GEN

T1 - World-GAN

T2 - 2021 IEEE Conference on Games, CoG 2021

AU - Awiszus, Maren

AU - Schubert, Frederik

AU - Rosenhahn, Bodo

N1 - Funding Information: VI. ACKNOWLEDGMENT This work has been supported by the Federal Ministry of Education and Research (BMBF), Germany, under the project LeibnizKILabor (grant no. 01DD20003), the Federal Ministry for Economic Affairs and Energy under the Wipano programme ”NaturalAI” (03THW05K06), the Center for Digital Innovations (ZDIN) and the Deutsche Forschungsgemein-schaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122). Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.

AB - This work introduces World-GAN, the first method to perform data-driven Procedural Content Generation via Machine Learning in Minecraft from a single example. Based on a 3D Generative Adversarial Network (GAN) architecture, we are able to create arbitrarily sized world snippets from a given sample. We evaluate our approach on creations from the community as well as structures generated with the Minecraft World Generator. Our method is motivated by the dense representations used in Natural Language Processing (NLP) introduced with word2vec [1]. The proposed block2vec representations make World-GAN independent from the number of different blocks, which can vary a lot in Minecraft, and enable the generation of larger levels. Finally, we demonstrate that changing this new representation space allows us to change the generated style of an already trained generator. World-GAN enables its users to generate Minecraft worlds based on parts of their creations.

KW - GAN

KW - Generation

KW - Level

KW - Minecraft

KW - PCG

KW - Representation

KW - Scales

KW - Sin-GAN

KW - Single Example

KW - Style

UR - http://www.scopus.com/inward/record.url?scp=85120762636&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2106.10155

DO - 10.48550/arXiv.2106.10155

M3 - Conference contribution

AN - SCOPUS:85120762636

SN - 978-1-6654-4608-2

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

BT - 2021 IEEE Conference on Games, CoG 2021

PB - IEEE Computer Society

Y2 - 17 August 2021 through 20 August 2021

ER -

World-GAN: A Generative Model for Minecraft Worlds

Abstract

Publikationsreihe

Konferenz

ASJC Scopus Sachgebiete

Zugriff auf Dokument

Andere Dateien und Links

Projekte

PhoenixD: Exzellenzcluster 2122/1: Photonics, Optics, and Engineering – Innovation Across Disciplines

Dieses zitieren