An Evolutionary Algorithm Extended by Ecological Analogy and its Application to the Game of Go

Kojima, Takuya; Ueda, Kazuhiro; Nagano, Saburo

An Evolutionary Algorithm Extended by Ecological Analogy and its Application to the Game of Go

Takuya Kojima, Kazuhiro Ueda, Saburo Nagano

Download BibTeX Cite

Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Game Playing. Pages 684-690.

Abstract

The following two important features of human experts' knowledge are not realized by most evolutionary algorithms: one is that it is various and the other is that the amount of knowledge, including infrequently used knowledge, is large. To imitate these features, we introduce an activation value for individuals and a new variation-making operator, splitting, both of which are inspired by ecological systems. This algorithm is applied to the game of Go and a large amount of knowledge evaluated as appropriate by a human expert is acquired. Various kinds of Go knowledge may be acquired such as patterns, sequences of moves , and Go maxims, part of which has already been realized.

Takuya Kojima, Kazuhiro Ueda, and Saburo Nagano. 1997. An Evolutionary Algorithm Extended by Ecological Analogy and its Application to the Game of Go. In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97. IJCAI, 684–690. https://ijcai.org/proceedings/1997/100

@inproceedings{ijcai1997p100,
  title     = {An Evolutionary Algorithm Extended by Ecological Analogy and its Application to the Game of Go},
  author    = {Kojima, Takuya and Ueda, Kazuhiro and Nagano, Saburo},
  booktitle = {Proceedings of the Fifteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-97}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Martha E. Pollack},
  pages     = {684--690},
  year      = {1997},
  note      = {Game Playing},
  url       = {https://ijcai.org/proceedings/1997/100},
}

TY  - CPAPER
TI  - An Evolutionary Algorithm Extended by Ecological Analogy and its Application to the Game of Go
AU  - Kojima, Takuya
AU  - Ueda, Kazuhiro
AU  - Nagano, Saburo
T2  - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1997
SP  - 684
EP  - 690
UR  - https://ijcai.org/proceedings/1997/100
ER  -