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

3 Citations (Scopus)

246 Downloads (Pure)

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
Pages (from-to)	19–31
Number of pages	13
Journal	Kunstliche Intelligenz
Volume	34
Issue number	1
Early online date	18 Jan 2020
DOIs	https://doi.org/10.1007/s13218-020-00635-0
Publication status	Published - 1 Mar 2020

Access to Document

10.1007/s13218-020-00635-0Licence: Other

GDMC___1st_year - author postprint
© 2020 Springer-Verlag. This is a post-peer-review, pre-copyedit version of an article published in KI - Künstliche Intelligenz volume. The final authenticated version is available online at: https://doi.org/10.1007/s13218-020-00635-0
Accepted author manuscript, 48.5 MBLicence: Other

https://rdcu.be/b2kiWLicence: Unspecified

Cite this

@article{aa330b9aea794a11a7e7b7ac13dc20ab,

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.",

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 = "{\textcopyright} 2020 Springer-Verlag. This is a post-peer-review, pre-copyedit version of an article published in KI - K{\"u}nstliche Intelligenz. The final authenticated version is available online at: https://doi.org/10.1007/s13218-020-00635-0.",

year = "2020",

month = mar,

day = "1",

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

language = "English",

volume = "34",

pages = "19–31",

journal = "Kunstliche Intelligenz",

issn = "1610-1987",

publisher = "Springer Nature Link",

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 - © 2020 Springer-Verlag. This is a post-peer-review, pre-copyedit version of an article published in KI - Künstliche Intelligenz. The final authenticated version is available online at: https://doi.org/10.1007/s13218-020-00635-0.

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.

U2 - 10.1007/s13218-020-00635-0

DO - 10.1007/s13218-020-00635-0

M3 - Article

SN - 1610-1987

VL - 34

SP - 19

EP - 31

JO - Kunstliche Intelligenz

JF - Kunstliche Intelligenz

IS - 1

ER -