# $\delta$-logit : Dynamic Difficulty Adjustment Using Few Data Points

1 CEDRIC - ILJ - CEDRIC - Interactivité pour Lire et Jouer
CEDRIC - Centre d'études et de recherche en informatique et communications
Abstract : Difficulty is a fundamental factor of enjoyment and motivation in video games. Thus, many video games use Dynamic Difficulty Adjustment systems to provide players with an optimal level of challenge. However, many of these systems are either game specific, limited to a specific range of difficulties, or require much more data than one can track during a short play session. In this paper, we introduce the δ-logit algorithm. It can be used on many game types, allows a developer to set the game's difficulty to any level, with, in our experiment, a player failure error prediction rate lower than 20% in less than two minutes of playtime. In order to roughly estimate the difficulty as quickly as possible , δ-logit drives a single metavariable to adjust the game's difficulty. It starts with a simple +/-δ algorithm to gather a few data points and then uses logistic regression to estimate the players failure probability when the smallest required amount of data has been collected. The goal of this paper is to describe δ-logit and estimate its accuracy and convergence speed with a study on 37 participants playing a tank shooter game.
Keywords :
Document type :
Conference papers
Domain :
Complete list of metadatas

Cited literature [26 references]

https://hal.archives-ouvertes.fr/hal-02436725
Contributor : Levieux Guillaume <>
Submitted on : Monday, January 13, 2020 - 12:23:59 PM
Last modification on : Thursday, February 27, 2020 - 5:21:38 PM

### File

icec2019.pdf
Files produced by the author(s)

### Citation

William Rao Fernandes, Guillaume Levieux. $\delta$-logit : Dynamic Difficulty Adjustment Using Few Data Points. ICEC - International Conférence on Entertainment Computing, Sep 2019, Arequipa, Peru. pp.158-171, ⟨10.1007/978-3-030-34644-7_13⟩. ⟨hal-02436725⟩

Record views