A simple hybrid algorithm for improving team sport AI

David J. King, D Edwards

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Downloads (Pure)

Abstract

In the very popular genre of team sports games defeating the opposing AI is the main focus of the gameplay experience. However the overall quality of these games is significantly damaged because, in a lot of cases, the opposition is prone to mistakes or vulnerable to exploitation. This paper introduces an AI system which overcomes this failing through the addition of simple adaptive learning and prediction algorithms to a basic ice hockey defence. The paper shows that improvements can be made to the gameplay experience without overly increasing the implementation complexity of the system or negatively affecting its performance. The created defensive system detects patterns in the offensive tactics used against it and changes elements of its reaction accordingly; effectively adapting to attempted exploitation of repeated tactics. This is achieved using a fuzzy inference system that tracks player movement, which greatly improves variation of defender positioning, alongside an N-gram pattern recognition-based algorithm that predicts the next action of the attacking player. Analysis of implementation complexity and execution overhead shows that these techniques are not prohibitively expensive in either respect, and are therefore appropriate for use in games.
Original languageEnglish
Title of host publicationProceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation
EditorsSander Bakkes, Frank Nack
Place of PublicationOstend
PublisherEUROSIS
Pages63-67
Number of pages5
ISBN (Print)9789077381915
Publication statusPublished - 2015
EventGameOn 2015, 16th International Conference on Intelligent Games and Simulation - University of Amsterdam, Amsterdam, Netherlands
Duration: 2 Dec 20154 Dec 2015
Conference number: 16th

Conference

ConferenceGameOn 2015, 16th International Conference on Intelligent Games and Simulation
CountryNetherlands
CityAmsterdam
Period2/12/154/12/15

Fingerprint

Sports
Fuzzy inference
Pattern recognition
Ice

Cite this

King, D. J., & Edwards, D. (2015). A simple hybrid algorithm for improving team sport AI. In S. Bakkes, & F. Nack (Eds.), Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation (pp. 63-67). Ostend: EUROSIS.
King, David J. ; Edwards, D. / A simple hybrid algorithm for improving team sport AI. Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation. editor / Sander Bakkes ; Frank Nack. Ostend : EUROSIS, 2015. pp. 63-67
@inproceedings{355751d396664f978c2bddb709af6a53,
title = "A simple hybrid algorithm for improving team sport AI",
abstract = "In the very popular genre of team sports games defeating the opposing AI is the main focus of the gameplay experience. However the overall quality of these games is significantly damaged because, in a lot of cases, the opposition is prone to mistakes or vulnerable to exploitation. This paper introduces an AI system which overcomes this failing through the addition of simple adaptive learning and prediction algorithms to a basic ice hockey defence. The paper shows that improvements can be made to the gameplay experience without overly increasing the implementation complexity of the system or negatively affecting its performance. The created defensive system detects patterns in the offensive tactics used against it and changes elements of its reaction accordingly; effectively adapting to attempted exploitation of repeated tactics. This is achieved using a fuzzy inference system that tracks player movement, which greatly improves variation of defender positioning, alongside an N-gram pattern recognition-based algorithm that predicts the next action of the attacking player. Analysis of implementation complexity and execution overhead shows that these techniques are not prohibitively expensive in either respect, and are therefore appropriate for use in games.",
author = "King, {David J.} and D Edwards",
year = "2015",
language = "English",
isbn = "9789077381915",
pages = "63--67",
editor = "Sander Bakkes and Frank Nack",
booktitle = "Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation",
publisher = "EUROSIS",

}

King, DJ & Edwards, D 2015, A simple hybrid algorithm for improving team sport AI. in S Bakkes & F Nack (eds), Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation. EUROSIS, Ostend, pp. 63-67, GameOn 2015, 16th International Conference on Intelligent Games and Simulation, Amsterdam, Netherlands, 2/12/15.

A simple hybrid algorithm for improving team sport AI. / King, David J.; Edwards, D.

Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation. ed. / Sander Bakkes; Frank Nack. Ostend : EUROSIS, 2015. p. 63-67.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A simple hybrid algorithm for improving team sport AI

AU - King, David J.

AU - Edwards, D

PY - 2015

Y1 - 2015

N2 - In the very popular genre of team sports games defeating the opposing AI is the main focus of the gameplay experience. However the overall quality of these games is significantly damaged because, in a lot of cases, the opposition is prone to mistakes or vulnerable to exploitation. This paper introduces an AI system which overcomes this failing through the addition of simple adaptive learning and prediction algorithms to a basic ice hockey defence. The paper shows that improvements can be made to the gameplay experience without overly increasing the implementation complexity of the system or negatively affecting its performance. The created defensive system detects patterns in the offensive tactics used against it and changes elements of its reaction accordingly; effectively adapting to attempted exploitation of repeated tactics. This is achieved using a fuzzy inference system that tracks player movement, which greatly improves variation of defender positioning, alongside an N-gram pattern recognition-based algorithm that predicts the next action of the attacking player. Analysis of implementation complexity and execution overhead shows that these techniques are not prohibitively expensive in either respect, and are therefore appropriate for use in games.

AB - In the very popular genre of team sports games defeating the opposing AI is the main focus of the gameplay experience. However the overall quality of these games is significantly damaged because, in a lot of cases, the opposition is prone to mistakes or vulnerable to exploitation. This paper introduces an AI system which overcomes this failing through the addition of simple adaptive learning and prediction algorithms to a basic ice hockey defence. The paper shows that improvements can be made to the gameplay experience without overly increasing the implementation complexity of the system or negatively affecting its performance. The created defensive system detects patterns in the offensive tactics used against it and changes elements of its reaction accordingly; effectively adapting to attempted exploitation of repeated tactics. This is achieved using a fuzzy inference system that tracks player movement, which greatly improves variation of defender positioning, alongside an N-gram pattern recognition-based algorithm that predicts the next action of the attacking player. Analysis of implementation complexity and execution overhead shows that these techniques are not prohibitively expensive in either respect, and are therefore appropriate for use in games.

M3 - Conference contribution

SN - 9789077381915

SP - 63

EP - 67

BT - Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation

A2 - Bakkes, Sander

A2 - Nack, Frank

PB - EUROSIS

CY - Ostend

ER -

King DJ, Edwards D. A simple hybrid algorithm for improving team sport AI. In Bakkes S, Nack F, editors, Proceedings of GameOn’2015, 16th International Conference on Intelligent Games and Simulation. Ostend: EUROSIS. 2015. p. 63-67