The AI Settlement Generation Challenge in Minecraft: First Year Report

Christoph Salge; Michael Cerny Green; Rodrigo Canaan; Filip Skwarski; Rafael Fritsch; Adrian Brightmoore; Shaofang Ye; Changxing Cao; Julian Togelius

doi:10.1007/s13218-020-00635-0

The AI Settlement Generation Challenge in Minecraft: First Year Report

Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Filip Skwarski, Rafael Fritsch, Adrian Brightmoore, Shaofang Ye, Changxing Cao, Julian Togelius

Research output: Contribution to journal › Article › peer-review

Abstract

This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map. This challenge seeks to focus research into adaptive and holistic procedural content generation. Generating Minecraft towns and villages given existing maps is a suitable task for this, as it requires the generated content to be adaptive, functional, evocative and aesthetic at the same time. Here, we present the results from the first iteration of the competition. We discuss the evaluation methodology, present the different technical approaches by the competitors, and outline the open problems.

Original language	English (US)
Pages (from-to)	19-31
Number of pages	13
Journal	KI - Kunstliche Intelligenz
Volume	34
Issue number	1
DOIs	https://doi.org/10.1007/s13218-020-00635-0
State	Published - Mar 1 2020

Keywords

Competition
Generative design
Minecraft
Procedural content generation

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.1007/s13218-020-00635-0

Cite this

@article{ee579be7a5c442ff86419e3e3d098d24,

title = "The AI Settlement Generation Challenge in Minecraft: First Year Report",

abstract = "This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map. This challenge seeks to focus research into adaptive and holistic procedural content generation. Generating Minecraft towns and villages given existing maps is a suitable task for this, as it requires the generated content to be adaptive, functional, evocative and aesthetic at the same time. Here, we present the results from the first iteration of the competition. We discuss the evaluation methodology, present the different technical approaches by the competitors, and outline the open problems.",

keywords = "Competition, Generative design, Minecraft, Procedural content generation",

author = "Christoph Salge and Green, {Michael Cerny} and Rodrigo Canaan and Filip Skwarski and Rafael Fritsch and Adrian Brightmoore and Shaofang Ye and Changxing Cao and Julian Togelius",

note = "Funding Information: CS is funded by the EU Horizon 2020 programme/Marie Sklodowska- Curie grant 705643. RC gratefully acknowledges the financial support from Honda Research Institute Europe (HRI-EU). Michael Cerny Green acknowledges the financial support of the GAANN program. Many thanks to our panel of expert judges who donated their time to evaluate the different entries. Also thanks to Squirrel Eiserloh for providing us with screenshots used in this paper. Publisher Copyright: {\textcopyright} 2020, Gesellschaft f{\"u}r Informatik e.V. and Springer-Verlag GmbH Germany, part of Springer Nature.",

year = "2020",

month = mar,

day = "1",

doi = "10.1007/s13218-020-00635-0",

language = "English (US)",

volume = "34",

pages = "19--31",

journal = "KI - Kunstliche Intelligenz",

issn = "0933-1875",

publisher = "Springer International Publishing",

number = "1",

}

TY - JOUR

T1 - The AI Settlement Generation Challenge in Minecraft

T2 - First Year Report

AU - Salge, Christoph

AU - Green, Michael Cerny

AU - Canaan, Rodrigo

AU - Skwarski, Filip

AU - Fritsch, Rafael

AU - Brightmoore, Adrian

AU - Ye, Shaofang

AU - Cao, Changxing

AU - Togelius, Julian

N1 - Funding Information: CS is funded by the EU Horizon 2020 programme/Marie Sklodowska- Curie grant 705643. RC gratefully acknowledges the financial support from Honda Research Institute Europe (HRI-EU). Michael Cerny Green acknowledges the financial support of the GAANN program. Many thanks to our panel of expert judges who donated their time to evaluate the different entries. Also thanks to Squirrel Eiserloh for providing us with screenshots used in this paper. Publisher Copyright: © 2020, Gesellschaft für Informatik e.V. and Springer-Verlag GmbH Germany, part of Springer Nature.

PY - 2020/3/1

Y1 - 2020/3/1

N2 - This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map. This challenge seeks to focus research into adaptive and holistic procedural content generation. Generating Minecraft towns and villages given existing maps is a suitable task for this, as it requires the generated content to be adaptive, functional, evocative and aesthetic at the same time. Here, we present the results from the first iteration of the competition. We discuss the evaluation methodology, present the different technical approaches by the competitors, and outline the open problems.

AB - This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map. This challenge seeks to focus research into adaptive and holistic procedural content generation. Generating Minecraft towns and villages given existing maps is a suitable task for this, as it requires the generated content to be adaptive, functional, evocative and aesthetic at the same time. Here, we present the results from the first iteration of the competition. We discuss the evaluation methodology, present the different technical approaches by the competitors, and outline the open problems.

KW - Competition

KW - Generative design

KW - Minecraft

KW - Procedural content generation

UR - http://www.scopus.com/inward/record.url?scp=85088509631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088509631&partnerID=8YFLogxK

U2 - 10.1007/s13218-020-00635-0

DO - 10.1007/s13218-020-00635-0

M3 - Article

AN - SCOPUS:85088509631

SN - 0933-1875

VL - 34

SP - 19

EP - 31

JO - KI - Kunstliche Intelligenz

JF - KI - Kunstliche Intelligenz

IS - 1

ER -

The AI Settlement Generation Challenge in Minecraft: First Year Report

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this