Deakin University
Browse

File(s) under embargo

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

conference contribution
posted on 2023-08-24, 05:17 authored by S Demediuk, M Tamassia, X Li, WL Raffe
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.

History

Location

AUSTRALIA, Sydney

Start date

2019-01-29

End date

2019-01-31

ISBN-13

9781450366038

Language

English

Title of proceedings

ACM International Conference Proceeding Series

Event

Australasian Computer Science Week Multiconference (ACSW)

Publisher

ASSOC COMPUTING MACHINERY

Place of publication

New York, N.Y.