Hybrid of evolution and reinforcement learning for othello players

Kyung Joong Kim, Heejin Choi, Sung Bae Cho

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

19 Citations (Scopus)

Abstract

Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007
Pages203-209
Number of pages7
DOIs
Publication statusPublished - 2007 Sep 25
Event2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007 - Honolulu, HI, United States
Duration: 2007 Apr 12007 Apr 5

Publication series

NameProceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007

Other

Other2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007
CountryUnited States
CityHonolulu, HI
Period07/4/107/4/5

Fingerprint

Reinforcement learning
Reinforcement Learning
Evolutionary algorithms
Evolutionary Algorithms
Domain Knowledge
Initialization
Exploitation
Learning algorithms
Learning Algorithm
Game
Resources
Optimization
Evaluation
Experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Electrical and Electronic Engineering
  • Computational Mathematics
  • Theoretical Computer Science

Cite this

Kim, K. J., Choi, H., & Cho, S. B. (2007). Hybrid of evolution and reinforcement learning for othello players. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007 (pp. 203-209). [4219044] (Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007). https://doi.org/10.1109/CIG.2007.368099
Kim, Kyung Joong ; Choi, Heejin ; Cho, Sung Bae. / Hybrid of evolution and reinforcement learning for othello players. Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007. 2007. pp. 203-209 (Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007).
@inproceedings{358ab3b9ab95467b86cd0bc57b8a3c22,
title = "Hybrid of evolution and reinforcement learning for othello players",
abstract = "Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.",
author = "Kim, {Kyung Joong} and Heejin Choi and Cho, {Sung Bae}",
year = "2007",
month = "9",
day = "25",
doi = "10.1109/CIG.2007.368099",
language = "English",
isbn = "1424407095",
series = "Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007",
pages = "203--209",
booktitle = "Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007",

}

Kim, KJ, Choi, H & Cho, SB 2007, Hybrid of evolution and reinforcement learning for othello players. in Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007., 4219044, Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007, pp. 203-209, 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007, Honolulu, HI, United States, 07/4/1. https://doi.org/10.1109/CIG.2007.368099

Hybrid of evolution and reinforcement learning for othello players. / Kim, Kyung Joong; Choi, Heejin; Cho, Sung Bae.

Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007. 2007. p. 203-209 4219044 (Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007).

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

TY - GEN

T1 - Hybrid of evolution and reinforcement learning for othello players

AU - Kim, Kyung Joong

AU - Choi, Heejin

AU - Cho, Sung Bae

PY - 2007/9/25

Y1 - 2007/9/25

N2 - Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.

AB - Although the reinforcement learning and evolutionary algorithm show good results in board evaluation optimization, the hybrid of both approaches is rarely addressed in the literature. In this paper, the evolutionary algorithm is boosted using resources from the reinforcement learning. 1) The initialization of initial population using solution optimized by temporal difference learning 2) Exploitation of domain knowledge extracted from reinforcement learning. Experiments on Othello game strategies show that the proposed methods can effectively search the solution space and improve the performance.

UR - http://www.scopus.com/inward/record.url?scp=34548767008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548767008&partnerID=8YFLogxK

U2 - 10.1109/CIG.2007.368099

DO - 10.1109/CIG.2007.368099

M3 - Conference contribution

AN - SCOPUS:34548767008

SN - 1424407095

SN - 9781424407095

T3 - Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007

SP - 203

EP - 209

BT - Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007

ER -

Kim KJ, Choi H, Cho SB. Hybrid of evolution and reinforcement learning for othello players. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007. 2007. p. 203-209. 4219044. (Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, CIG 2007). https://doi.org/10.1109/CIG.2007.368099