Recognizing player's activities and hidden state

Wesley Kerr, Paul R Cohen, Niall Adams

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

1 Citation (Scopus)

Abstract

This paper describes a machine learning approach to classifying the activities of players in games. Instances of activities generally are not identical because they play out in different contexts, so the challenge is to extract the "essences" of activities from instances. We show how this problem may be mapped to a sequence alignment problem, for which there are polynomial-time solutions. The method works well even when some features of activities are not observable (e.g., the emotional states of players). In fact, these features can in some conditions be inferred with high accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011
Pages84-90
Number of pages7
DOIs
StatePublished - 2011
Event6th International Conference on the Foundations of Digital Games, FDG 2011 - Bordeaux, France
Duration: Jun 29 2011Jul 1 2011

Other

Other6th International Conference on the Foundations of Digital Games, FDG 2011
CountryFrance
CityBordeaux
Period6/29/117/1/11

Fingerprint

Learning systems
Polynomials

Keywords

  • Activity classification
  • Hidden state
  • Machine learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Kerr, W., Cohen, P. R., & Adams, N. (2011). Recognizing player's activities and hidden state. In Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011 (pp. 84-90) https://doi.org/10.1145/2159365.2159377

Recognizing player's activities and hidden state. / Kerr, Wesley; Cohen, Paul R; Adams, Niall.

Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011. 2011. p. 84-90.

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

Kerr, W, Cohen, PR & Adams, N 2011, Recognizing player's activities and hidden state. in Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011. pp. 84-90, 6th International Conference on the Foundations of Digital Games, FDG 2011, Bordeaux, France, 6/29/11. https://doi.org/10.1145/2159365.2159377
Kerr W, Cohen PR, Adams N. Recognizing player's activities and hidden state. In Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011. 2011. p. 84-90 https://doi.org/10.1145/2159365.2159377
Kerr, Wesley ; Cohen, Paul R ; Adams, Niall. / Recognizing player's activities and hidden state. Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011. 2011. pp. 84-90
@inproceedings{38c079ae96ab4154ad22d7ba7db0978f,
title = "Recognizing player's activities and hidden state",
abstract = "This paper describes a machine learning approach to classifying the activities of players in games. Instances of activities generally are not identical because they play out in different contexts, so the challenge is to extract the {"}essences{"} of activities from instances. We show how this problem may be mapped to a sequence alignment problem, for which there are polynomial-time solutions. The method works well even when some features of activities are not observable (e.g., the emotional states of players). In fact, these features can in some conditions be inferred with high accuracy.",
keywords = "Activity classification, Hidden state, Machine learning",
author = "Wesley Kerr and Cohen, {Paul R} and Niall Adams",
year = "2011",
doi = "10.1145/2159365.2159377",
language = "English (US)",
isbn = "9781450308045",
pages = "84--90",
booktitle = "Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011",

}

TY - GEN

T1 - Recognizing player's activities and hidden state

AU - Kerr, Wesley

AU - Cohen, Paul R

AU - Adams, Niall

PY - 2011

Y1 - 2011

N2 - This paper describes a machine learning approach to classifying the activities of players in games. Instances of activities generally are not identical because they play out in different contexts, so the challenge is to extract the "essences" of activities from instances. We show how this problem may be mapped to a sequence alignment problem, for which there are polynomial-time solutions. The method works well even when some features of activities are not observable (e.g., the emotional states of players). In fact, these features can in some conditions be inferred with high accuracy.

AB - This paper describes a machine learning approach to classifying the activities of players in games. Instances of activities generally are not identical because they play out in different contexts, so the challenge is to extract the "essences" of activities from instances. We show how this problem may be mapped to a sequence alignment problem, for which there are polynomial-time solutions. The method works well even when some features of activities are not observable (e.g., the emotional states of players). In fact, these features can in some conditions be inferred with high accuracy.

KW - Activity classification

KW - Hidden state

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=84858970960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858970960&partnerID=8YFLogxK

U2 - 10.1145/2159365.2159377

DO - 10.1145/2159365.2159377

M3 - Conference contribution

SN - 9781450308045

SP - 84

EP - 90

BT - Proceedings of the 6th International Conference on the Foundations of Digital Games, FDG 2011

ER -