Evolving speciated checkers players with crowding algorithm

Kyung Joong Kim, Sung Bae Cho

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

Conventional evolutionary algorithms have a property that only one solution often dominates and it is sometimes useful to find diverse solutions and combine them because there might be many different solutions to one problem in real-world problems. Recently, developing checkers players using evolutionary algorithms has been widely exploited to show the power of evolution for machine learning. In this paper, we propose an evolutionary checkers player that is developed by a speciation technique called the "crowding algorithm". In many experiments, our checkers player with an ensemble structure showed better performance than non-speciated checkers players. A neural network is used to validate the game board, and a min-max search finds the optimal board. The neural network evaluator is evolved using the evolutionary algorithm.

Original languageEnglish
Pages407-412
Number of pages6
DOIs
Publication statusPublished - 2002 Jan 1
Event2002 Congress on Evolutionary Computation, CEC 2002 - Honolulu, HI, United States
Duration: 2002 May 122002 May 17

Other

Other2002 Congress on Evolutionary Computation, CEC 2002
CountryUnited States
CityHonolulu, HI
Period02/5/1202/5/17

Fingerprint

Evolutionary algorithms
Neural networks
Learning systems
Experiments

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Kim, K. J., & Cho, S. B. (2002). Evolving speciated checkers players with crowding algorithm. 407-412. Paper presented at 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States. https://doi.org/10.1109/CEC.2002.1006269
Kim, Kyung Joong ; Cho, Sung Bae. / Evolving speciated checkers players with crowding algorithm. Paper presented at 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States.6 p.
@conference{b43b2e41b0954fe0806afcc37a5e4c13,
title = "Evolving speciated checkers players with crowding algorithm",
abstract = "Conventional evolutionary algorithms have a property that only one solution often dominates and it is sometimes useful to find diverse solutions and combine them because there might be many different solutions to one problem in real-world problems. Recently, developing checkers players using evolutionary algorithms has been widely exploited to show the power of evolution for machine learning. In this paper, we propose an evolutionary checkers player that is developed by a speciation technique called the {"}crowding algorithm{"}. In many experiments, our checkers player with an ensemble structure showed better performance than non-speciated checkers players. A neural network is used to validate the game board, and a min-max search finds the optimal board. The neural network evaluator is evolved using the evolutionary algorithm.",
author = "Kim, {Kyung Joong} and Cho, {Sung Bae}",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/CEC.2002.1006269",
language = "English",
pages = "407--412",
note = "2002 Congress on Evolutionary Computation, CEC 2002 ; Conference date: 12-05-2002 Through 17-05-2002",

}

Kim, KJ & Cho, SB 2002, 'Evolving speciated checkers players with crowding algorithm' Paper presented at 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States, 02/5/12 - 02/5/17, pp. 407-412. https://doi.org/10.1109/CEC.2002.1006269

Evolving speciated checkers players with crowding algorithm. / Kim, Kyung Joong; Cho, Sung Bae.

2002. 407-412 Paper presented at 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Evolving speciated checkers players with crowding algorithm

AU - Kim, Kyung Joong

AU - Cho, Sung Bae

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Conventional evolutionary algorithms have a property that only one solution often dominates and it is sometimes useful to find diverse solutions and combine them because there might be many different solutions to one problem in real-world problems. Recently, developing checkers players using evolutionary algorithms has been widely exploited to show the power of evolution for machine learning. In this paper, we propose an evolutionary checkers player that is developed by a speciation technique called the "crowding algorithm". In many experiments, our checkers player with an ensemble structure showed better performance than non-speciated checkers players. A neural network is used to validate the game board, and a min-max search finds the optimal board. The neural network evaluator is evolved using the evolutionary algorithm.

AB - Conventional evolutionary algorithms have a property that only one solution often dominates and it is sometimes useful to find diverse solutions and combine them because there might be many different solutions to one problem in real-world problems. Recently, developing checkers players using evolutionary algorithms has been widely exploited to show the power of evolution for machine learning. In this paper, we propose an evolutionary checkers player that is developed by a speciation technique called the "crowding algorithm". In many experiments, our checkers player with an ensemble structure showed better performance than non-speciated checkers players. A neural network is used to validate the game board, and a min-max search finds the optimal board. The neural network evaluator is evolved using the evolutionary algorithm.

UR - http://www.scopus.com/inward/record.url?scp=29244440658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29244440658&partnerID=8YFLogxK

U2 - 10.1109/CEC.2002.1006269

DO - 10.1109/CEC.2002.1006269

M3 - Paper

AN - SCOPUS:29244440658

SP - 407

EP - 412

ER -

Kim KJ, Cho SB. Evolving speciated checkers players with crowding algorithm. 2002. Paper presented at 2002 Congress on Evolutionary Computation, CEC 2002, Honolulu, HI, United States. https://doi.org/10.1109/CEC.2002.1006269