Challenging AI: Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment

Simon Peter Demediuk; Marco Tamassia; Xiaodong Li; William Raffe

doi:10.1145/3290688.3290748

Challenging AI: Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment

Simon Peter Demediuk, Marco Tamassia, Xiaodong Li, William Raffe

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Providing a challenging Artificial Intelligent opponent is an important aspect of making video games enjoyable and immersive. A game that is too easy, or conversely too hard may frustrate or bore players. Dynamic Difficulty Adjustment is a method that aims at improving the traditional methods of difficulty selection, by providing an opponent that tailors the challenge it presents to players such that it is at an optimal level for them. This research presents a player evaluation of three different Dynamic Difficulty Adjustment approaches using Monte Carlo Tree Search and measures their impact on player enjoyment, realism and perceived level of difficulty. In particular, it investigates the effect that different win/loss ratios, employed by Dynamic Difficulty Adjustment, have on player enjoyment.

Original language	English
Title of host publication	Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2019
Publisher	ACM
ISBN (Electronic)	9781450366038
DOIs	https://doi.org/10.1145/3290688.3290748
Publication status	Published - 29 Jan 2019

Publication series

Name	ACM International Conference Proceeding Series

Keywords

Artificial intelligence
Dynamic Difficulty Adjustment
Monte Carlo Tree Search
Video Games

Access to Document

10.1145/3290688.3290748

Cite this

@inproceedings{fc523797117d4d41920329b60ae8c556,

title = "Challenging AI: Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment",

abstract = "Providing a challenging Artificial Intelligent opponent is an important aspect of making video games enjoyable and immersive. A game that is too easy, or conversely too hard may frustrate or bore players. Dynamic Difficulty Adjustment is a method that aims at improving the traditional methods of difficulty selection, by providing an opponent that tailors the challenge it presents to players such that it is at an optimal level for them. This research presents a player evaluation of three different Dynamic Difficulty Adjustment approaches using Monte Carlo Tree Search and measures their impact on player enjoyment, realism and perceived level of difficulty. In particular, it investigates the effect that different win/loss ratios, employed by Dynamic Difficulty Adjustment, have on player enjoyment.",

keywords = "Artificial intelligence, Dynamic Difficulty Adjustment, Monte Carlo Tree Search, Video Games",

author = "Demediuk, {Simon Peter} and Marco Tamassia and Xiaodong Li and William Raffe",

year = "2019",

month = jan,

day = "29",

doi = "10.1145/3290688.3290748",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "ACM",

booktitle = "Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2019",

address = "United States",

}

Challenging AI: Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment. / Demediuk, Simon Peter; Tamassia, Marco; Li, Xiaodong et al.
Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2019. ACM, 2019. a43 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Challenging AI

T2 - Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment

AU - Demediuk, Simon Peter

AU - Tamassia, Marco

AU - Li, Xiaodong

AU - Raffe, William

PY - 2019/1/29

Y1 - 2019/1/29

N2 - Providing a challenging Artificial Intelligent opponent is an important aspect of making video games enjoyable and immersive. A game that is too easy, or conversely too hard may frustrate or bore players. Dynamic Difficulty Adjustment is a method that aims at improving the traditional methods of difficulty selection, by providing an opponent that tailors the challenge it presents to players such that it is at an optimal level for them. This research presents a player evaluation of three different Dynamic Difficulty Adjustment approaches using Monte Carlo Tree Search and measures their impact on player enjoyment, realism and perceived level of difficulty. In particular, it investigates the effect that different win/loss ratios, employed by Dynamic Difficulty Adjustment, have on player enjoyment.

AB - Providing a challenging Artificial Intelligent opponent is an important aspect of making video games enjoyable and immersive. A game that is too easy, or conversely too hard may frustrate or bore players. Dynamic Difficulty Adjustment is a method that aims at improving the traditional methods of difficulty selection, by providing an opponent that tailors the challenge it presents to players such that it is at an optimal level for them. This research presents a player evaluation of three different Dynamic Difficulty Adjustment approaches using Monte Carlo Tree Search and measures their impact on player enjoyment, realism and perceived level of difficulty. In particular, it investigates the effect that different win/loss ratios, employed by Dynamic Difficulty Adjustment, have on player enjoyment.

KW - Artificial intelligence

KW - Dynamic Difficulty Adjustment

KW - Monte Carlo Tree Search

KW - Video Games

UR - http://www.scopus.com/inward/record.url?scp=85061254548&partnerID=8YFLogxK

U2 - 10.1145/3290688.3290748

DO - 10.1145/3290688.3290748

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2019

PB - ACM

ER -

Challenging AI: Evaluating the Effect of MCTS-Driven Dynamic Difficulty Adjustment on Player Enjoyment

Abstract

Publication series

Keywords

Access to Document

Other files and links

Cite this