Current Frontiers in Computer Go

Abstract : This paper presents the recent technical advances in Monte-Carlo Tree Search for the Game of Go, shows the many similarities and the rare differences between the current best programs, and reports the results of the computer-Go event organized at FUZZ-IEEE 2009, in which four main Go programs played against top level humans. We see that in 9x9, computers are very close to the best human level, and can be improved easily for the opening book; whereas in 19x19, handicap 7 is not enough for the computers to win against top level professional players, due to some clearly understood (but not solved) weaknesses of the current algorithms. Applications far from the game of Go are also cited. Importantly, the first ever win of a computer against a 9th Dan professional player in 9x9 Go occurred in this event.
Document type :
Journal articles
IEEE Transactions on Computational Intelligence and Artificial Intelligence in Games, IEEE, 2010, in press
Liste complète des métadonnées


https://hal.inria.fr/inria-00544622
Contributor : Olivier Teytaud <>
Submitted on : Thursday, December 9, 2010 - 10:08:20 AM
Last modification on : Thursday, February 9, 2017 - 4:01:40 PM
Document(s) archivé(s) le : Monday, November 5, 2012 - 12:40:24 PM

File

ct.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00544622, version 1

Citation

Arpad Rimmel, Olivier Teytaud, Chang-Shing Lee, Shi-Jim Yen, Mei-Hui Wang, et al.. Current Frontiers in Computer Go. IEEE Transactions on Computational Intelligence and Artificial Intelligence in Games, IEEE, 2010, in press. <inria-00544622>

Share

Metrics

Record views

236

Document downloads

686