Computer Go: A Grand Challenge to AI

Xindi Cai; Donald C. Wunsch

doi:10.1007/978-3-540-71984-7_16

Computer Go: A Grand Challenge to AI

Xindi Cai
, Donald C. Wunsch

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

The oriental game of Go is among the most tantalizing unconquered challenges in artificial intelligence after IBM's DEEP BLUE beat the world Chess champion in 1997. Its high branching factor prevents the conventional tree search approach, and long-range spatiotemporal interactions make position evaluation extremely difficult. Thus, Go attracts researchers from diverse fields who are attempting to understand how computers can represent human playing and win the game against humans. Numerous publications already exist on this topic with different motivations and a variety of application contexts. This chapter surveys methods and some related works used in computer Go published from 1970 until now, and offers a basic overview for future study. We also present our attempts and simulation results in building a non-knowledge game engine, using a novel hybrid evolutionary computation algorithm, for the Capture Go game.

Original language	American English
Title of host publication	Challenges for Computational Intelligence (Studies in Computational Intelligence, vol. 63)
DOIs	https://doi.org/10.1007/978-3-540-71984-7_16
State	Published - Jan 1 2007

Keywords

Computational intelligence

Disciplines

Electrical and Computer Engineering

Access to Document

10.1007/978-3-540-71984-7_16License: Unspecified

https://doi.org/10.1007/978-3-540-71984-7_16

Cite this

@inbook{3639209bcc7c43cf81b8e6c3efdbd414,

title = "Computer Go: A Grand Challenge to AI",

abstract = " The oriental game of Go is among the most tantalizing unconquered challenges in artificial intelligence after IBM's DEEP BLUE beat the world Chess champion in 1997. Its high branching factor prevents the conventional tree search approach, and long-range spatiotemporal interactions make position evaluation extremely difficult. Thus, Go attracts researchers from diverse fields who are attempting to understand how computers can represent human playing and win the game against humans. Numerous publications already exist on this topic with different motivations and a variety of application contexts. This chapter surveys methods and some related works used in computer Go published from 1970 until now, and offers a basic overview for future study. We also present our attempts and simulation results in building a non-knowledge game engine, using a novel hybrid evolutionary computation algorithm, for the Capture Go game.",

keywords = "Computational intelligence",

author = "Xindi Cai and Wunsch, \{Donald C.\}",

year = "2007",

month = jan,

day = "1",

doi = "10.1007/978-3-540-71984-7\_16",

language = "American English",

booktitle = "Challenges for Computational Intelligence (Studies in Computational Intelligence, vol. 63)",

}

TY - CHAP

T1 - Computer Go: A Grand Challenge to AI

AU - Cai, Xindi

AU - Wunsch, Donald C.

PY - 2007/1/1

Y1 - 2007/1/1

N2 - The oriental game of Go is among the most tantalizing unconquered challenges in artificial intelligence after IBM's DEEP BLUE beat the world Chess champion in 1997. Its high branching factor prevents the conventional tree search approach, and long-range spatiotemporal interactions make position evaluation extremely difficult. Thus, Go attracts researchers from diverse fields who are attempting to understand how computers can represent human playing and win the game against humans. Numerous publications already exist on this topic with different motivations and a variety of application contexts. This chapter surveys methods and some related works used in computer Go published from 1970 until now, and offers a basic overview for future study. We also present our attempts and simulation results in building a non-knowledge game engine, using a novel hybrid evolutionary computation algorithm, for the Capture Go game.

AB - The oriental game of Go is among the most tantalizing unconquered challenges in artificial intelligence after IBM's DEEP BLUE beat the world Chess champion in 1997. Its high branching factor prevents the conventional tree search approach, and long-range spatiotemporal interactions make position evaluation extremely difficult. Thus, Go attracts researchers from diverse fields who are attempting to understand how computers can represent human playing and win the game against humans. Numerous publications already exist on this topic with different motivations and a variety of application contexts. This chapter surveys methods and some related works used in computer Go published from 1970 until now, and offers a basic overview for future study. We also present our attempts and simulation results in building a non-knowledge game engine, using a novel hybrid evolutionary computation algorithm, for the Capture Go game.

KW - Computational intelligence

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/603

UR - https://doi.org/10.1007/978-3-540-71984-7_16

U2 - 10.1007/978-3-540-71984-7_16

DO - 10.1007/978-3-540-71984-7_16

M3 - Chapter

BT - Challenges for Computational Intelligence (Studies in Computational Intelligence, vol. 63)

ER -

Computer Go: A Grand Challenge to AI

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this