Machine Learning in Digital Games: A Survey

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.
LanguageEnglish
Pages123-161
JournalArtificial Intelligence Review
Volume29
Issue number2
DOIs
Publication statusPublished - 2008

Fingerprint

artificial intelligence
Artificial intelligence
Learning systems
learning
Reinforcement learning
reinforcement
Evolutionary algorithms
neural network
Neural networks
ability
Machine Learning
experience

Cite this

@article{84f12330756c47efa82fcb89fc264167,
title = "Machine Learning in Digital Games: A Survey",
abstract = "Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.",
author = "L. Galway and Darryl Charles and Michaela Black",
year = "2008",
doi = "10.1007/s10462-009-9112-y",
language = "English",
volume = "29",
pages = "123--161",
journal = "Artificial Intelligence Review",
issn = "0269-2821",
number = "2",

}

Machine Learning in Digital Games: A Survey. / Galway, L.; Charles, Darryl; Black, Michaela.

In: Artificial Intelligence Review, Vol. 29, No. 2, 2008, p. 123-161.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine Learning in Digital Games: A Survey

AU - Galway, L.

AU - Charles, Darryl

AU - Black, Michaela

PY - 2008

Y1 - 2008

N2 - Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.

AB - Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.

U2 - 10.1007/s10462-009-9112-y

DO - 10.1007/s10462-009-9112-y

M3 - Article

VL - 29

SP - 123

EP - 161

JO - Artificial Intelligence Review

T2 - Artificial Intelligence Review

JF - Artificial Intelligence Review

SN - 0269-2821

IS - 2

ER -