Ensemble approaches in evolutionary game strategies: A case study in Othello

Kyung Joong Kim, Sung Bae Cho

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

1 Citation (Scopus)

Abstract

In pattern recognition area, an ensemble approach is one of promising methods to increase the accuracy of classification systems. It is interesting to use the ensemble approach in evolving game strategies because they maintain a population of solutions simultaneously. Simply, an ensemble is formed from a set of strategies evolved in the last generation. There are many decision factors in the ensemble of game strategies: evolutionary algorithms, fusion methods, and the selection of members in the ensemble. In this paper, several evolutionary algorithms (evolutionary strategy, simple genetic algorithm, fitness sharing, and deterministic crowding algorithm) are compared with three representative fusion methods (majority voting, average, and weighted average) with selective ensembles (compared with the ensemble of all members). Additionally, the computational cost of an exhaustive search for the selective ensemble is reduced by introducing multi-stage evaluations. The ensemble approach is tested on the Othello game with a weight piece counter representation. The proposed ensemble approach outperforms the single best individual from the evolution and ensemble searching time is reasonable.

Original languageEnglish
Title of host publication2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
Pages212-219
Number of pages8
DOIs
Publication statusPublished - 2008 Dec 1
Event2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 - Perth, WA, Australia
Duration: 2008 Dec 152008 Dec 18

Publication series

Name2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008

Other

Other2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
CountryAustralia
CityPerth, WA
Period08/12/1508/12/18

Fingerprint

Evolutionary algorithms
Fusion reactions
Pattern recognition
Genetic algorithms
Costs

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Kim, K. J., & Cho, S. B. (2008). Ensemble approaches in evolutionary game strategies: A case study in Othello. In 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 (pp. 212-219). [5035642] (2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008). https://doi.org/10.1109/CIG.2008.5035642
Kim, Kyung Joong ; Cho, Sung Bae. / Ensemble approaches in evolutionary game strategies : A case study in Othello. 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. pp. 212-219 (2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008).
@inproceedings{e149e6e648414f8d8520f53e073faf84,
title = "Ensemble approaches in evolutionary game strategies: A case study in Othello",
abstract = "In pattern recognition area, an ensemble approach is one of promising methods to increase the accuracy of classification systems. It is interesting to use the ensemble approach in evolving game strategies because they maintain a population of solutions simultaneously. Simply, an ensemble is formed from a set of strategies evolved in the last generation. There are many decision factors in the ensemble of game strategies: evolutionary algorithms, fusion methods, and the selection of members in the ensemble. In this paper, several evolutionary algorithms (evolutionary strategy, simple genetic algorithm, fitness sharing, and deterministic crowding algorithm) are compared with three representative fusion methods (majority voting, average, and weighted average) with selective ensembles (compared with the ensemble of all members). Additionally, the computational cost of an exhaustive search for the selective ensemble is reduced by introducing multi-stage evaluations. The ensemble approach is tested on the Othello game with a weight piece counter representation. The proposed ensemble approach outperforms the single best individual from the evolution and ensemble searching time is reasonable.",
author = "Kim, {Kyung Joong} and Cho, {Sung Bae}",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/CIG.2008.5035642",
language = "English",
isbn = "9781424429745",
series = "2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008",
pages = "212--219",
booktitle = "2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008",

}

Kim, KJ & Cho, SB 2008, Ensemble approaches in evolutionary game strategies: A case study in Othello. in 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008., 5035642, 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008, pp. 212-219, 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008, Perth, WA, Australia, 08/12/15. https://doi.org/10.1109/CIG.2008.5035642

Ensemble approaches in evolutionary game strategies : A case study in Othello. / Kim, Kyung Joong; Cho, Sung Bae.

2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. p. 212-219 5035642 (2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008).

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

TY - GEN

T1 - Ensemble approaches in evolutionary game strategies

T2 - A case study in Othello

AU - Kim, Kyung Joong

AU - Cho, Sung Bae

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In pattern recognition area, an ensemble approach is one of promising methods to increase the accuracy of classification systems. It is interesting to use the ensemble approach in evolving game strategies because they maintain a population of solutions simultaneously. Simply, an ensemble is formed from a set of strategies evolved in the last generation. There are many decision factors in the ensemble of game strategies: evolutionary algorithms, fusion methods, and the selection of members in the ensemble. In this paper, several evolutionary algorithms (evolutionary strategy, simple genetic algorithm, fitness sharing, and deterministic crowding algorithm) are compared with three representative fusion methods (majority voting, average, and weighted average) with selective ensembles (compared with the ensemble of all members). Additionally, the computational cost of an exhaustive search for the selective ensemble is reduced by introducing multi-stage evaluations. The ensemble approach is tested on the Othello game with a weight piece counter representation. The proposed ensemble approach outperforms the single best individual from the evolution and ensemble searching time is reasonable.

AB - In pattern recognition area, an ensemble approach is one of promising methods to increase the accuracy of classification systems. It is interesting to use the ensemble approach in evolving game strategies because they maintain a population of solutions simultaneously. Simply, an ensemble is formed from a set of strategies evolved in the last generation. There are many decision factors in the ensemble of game strategies: evolutionary algorithms, fusion methods, and the selection of members in the ensemble. In this paper, several evolutionary algorithms (evolutionary strategy, simple genetic algorithm, fitness sharing, and deterministic crowding algorithm) are compared with three representative fusion methods (majority voting, average, and weighted average) with selective ensembles (compared with the ensemble of all members). Additionally, the computational cost of an exhaustive search for the selective ensemble is reduced by introducing multi-stage evaluations. The ensemble approach is tested on the Othello game with a weight piece counter representation. The proposed ensemble approach outperforms the single best individual from the evolution and ensemble searching time is reasonable.

UR - http://www.scopus.com/inward/record.url?scp=70349280484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349280484&partnerID=8YFLogxK

U2 - 10.1109/CIG.2008.5035642

DO - 10.1109/CIG.2008.5035642

M3 - Conference contribution

AN - SCOPUS:70349280484

SN - 9781424429745

T3 - 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008

SP - 212

EP - 219

BT - 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008

ER -

Kim KJ, Cho SB. Ensemble approaches in evolutionary game strategies: A case study in Othello. In 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. p. 212-219. 5035642. (2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008). https://doi.org/10.1109/CIG.2008.5035642