Generating Game Levels of Diverse Behaviour Engagement

Keyuan ZHANG; Jiayu BAI; Jialin LIU

doi:10.1109/CoG51982.2022.9893697

Generating Game Levels of Diverse Behaviour Engagement

Keyuan ZHANG, Jiayu BAI, Jialin LIU^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

4 Citations (Scopus)

Abstract

Recent years, there has been growing interests in experience-driven procedural level generation. Various metrics have been formulated to model player experience and help generate personalised levels. In this work, we question whether experience metrics can adapt to agents with different personas. We start by reviewing existing metrics for evaluating game levels. Then, focusing on platformer games, we design a framework integrating various agents and evaluation metrics. Experimental studies on Super Mario Bros. indicate that using the same evaluation metrics but agents with different personas can generate levels for particular persona. It implies that, for simple games, using a game-playing agent of specific player archetype as a level tester is probably all we need to generate levels of diverse behaviour engagement.

Original language	English
Title of host publication	Proceedings of the 2022 IEEE Conference on Games, CoG 2022
Publisher	IEEE Computer Society
Pages	167-174
Number of pages	8
ISBN (Electronic)	9781665459891
DOIs	https://doi.org/10.1109/CoG51982.2022.9893697
Publication status	Published - 2022
Externally published	Yes
Event	2022 IEEE Conference on Games, CoG 2022 - Beijing, China Duration: 21 Aug 2022 → 24 Aug 2022

Publication series

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
Volume	2022-August
ISSN (Print)	2325-4270
ISSN (Electronic)	2325-4289

Conference

Conference	2022 IEEE Conference on Games, CoG 2022
Country/Territory	China
City	Beijing
Period	21/08/22 → 24/08/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Funding

This work was supported by the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), the Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531), the Shenzhen Fundamental Research Program (Grant No. JCYJ20190809121403553), the National Natural Science Foundation of China (Grant No. 61906083), the Research Institute of Trustworthy Autonomous Systems (RITAS) and the SUSTech Undergraduate Teaching Quality and Reform Project (Grant No. SJZLGC202101). Corresponding author: Jialin Liu ([email protected]).

Keywords

Experience-driven procedural content generation
level generation
personalised levels
platformer games
player experience

Access to Document

10.1109/CoG51982.2022.9893697

Cite this

@inproceedings{818155fba4934984bb81cd2aaa024ff8,

title = "Generating Game Levels of Diverse Behaviour Engagement",

abstract = "Recent years, there has been growing interests in experience-driven procedural level generation. Various metrics have been formulated to model player experience and help generate personalised levels. In this work, we question whether experience metrics can adapt to agents with different personas. We start by reviewing existing metrics for evaluating game levels. Then, focusing on platformer games, we design a framework integrating various agents and evaluation metrics. Experimental studies on Super Mario Bros. indicate that using the same evaluation metrics but agents with different personas can generate levels for particular persona. It implies that, for simple games, using a game-playing agent of specific player archetype as a level tester is probably all we need to generate levels of diverse behaviour engagement.",

keywords = "Experience-driven procedural content generation, level generation, personalised levels, platformer games, player experience",

author = "Keyuan ZHANG and Jiayu BAI and Jialin LIU",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Conference on Games, CoG 2022 ; Conference date: 21-08-2022 Through 24-08-2022",

year = "2022",

doi = "10.1109/CoG51982.2022.9893697",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "167--174",

booktitle = "Proceedings of the 2022 IEEE Conference on Games, CoG 2022",

address = "United States",

}

ZHANG, K, BAI, J & LIU, J 2022, Generating Game Levels of Diverse Behaviour Engagement. in Proceedings of the 2022 IEEE Conference on Games, CoG 2022. IEEE Conference on Computatonal Intelligence and Games, CIG, vol. 2022-August, IEEE Computer Society, pp. 167-174, 2022 IEEE Conference on Games, CoG 2022, Beijing, China, 21/08/22. https://doi.org/10.1109/CoG51982.2022.9893697

Generating Game Levels of Diverse Behaviour Engagement. / ZHANG, Keyuan; BAI, Jiayu; LIU, Jialin.
Proceedings of the 2022 IEEE Conference on Games, CoG 2022. IEEE Computer Society, 2022. p. 167-174 (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2022-August).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - Generating Game Levels of Diverse Behaviour Engagement

AU - ZHANG, Keyuan

AU - BAI, Jiayu

AU - LIU, Jialin

PY - 2022

Y1 - 2022

N2 - Recent years, there has been growing interests in experience-driven procedural level generation. Various metrics have been formulated to model player experience and help generate personalised levels. In this work, we question whether experience metrics can adapt to agents with different personas. We start by reviewing existing metrics for evaluating game levels. Then, focusing on platformer games, we design a framework integrating various agents and evaluation metrics. Experimental studies on Super Mario Bros. indicate that using the same evaluation metrics but agents with different personas can generate levels for particular persona. It implies that, for simple games, using a game-playing agent of specific player archetype as a level tester is probably all we need to generate levels of diverse behaviour engagement.

AB - Recent years, there has been growing interests in experience-driven procedural level generation. Various metrics have been formulated to model player experience and help generate personalised levels. In this work, we question whether experience metrics can adapt to agents with different personas. We start by reviewing existing metrics for evaluating game levels. Then, focusing on platformer games, we design a framework integrating various agents and evaluation metrics. Experimental studies on Super Mario Bros. indicate that using the same evaluation metrics but agents with different personas can generate levels for particular persona. It implies that, for simple games, using a game-playing agent of specific player archetype as a level tester is probably all we need to generate levels of diverse behaviour engagement.

KW - Experience-driven procedural content generation

KW - level generation

KW - personalised levels

KW - platformer games

KW - player experience

UR - http://www.scopus.com/inward/record.url?scp=85139107216&partnerID=8YFLogxK

U2 - 10.1109/CoG51982.2022.9893697

DO - 10.1109/CoG51982.2022.9893697

M3 - Conference paper (refereed)

AN - SCOPUS:85139107216

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

SP - 167

EP - 174

BT - Proceedings of the 2022 IEEE Conference on Games, CoG 2022

PB - IEEE Computer Society

T2 - 2022 IEEE Conference on Games, CoG 2022

Y2 - 21 August 2022 through 24 August 2022

ER -

Generating Game Levels of Diverse Behaviour Engagement

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this