Monte Carlo go has a way to go

Haruhiro Yoshimoto, Kazuki Yoshizoe, Tomoyuki Kaneko, Akihiro Kishimoto, Kenjiro Taura

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

9 被引用数 (Scopus)

抄録

Monte Carlo Go is a promising method to improve the performance of computer Go programs. This approach determines the next move to play based on many Monte Carlo samples. This paper examines the relative advantages of additional samples and enhancements for Monte Carlo Go. By parallelizing Monte Carlo Go, we could increase sample sizes by two orders of magnitude. Experimental results obtained in 9 × 9 Go show strong evidence that there are trade-offs among these advantages and performance, indicating a way for Monte Carlo Go to go.

本文言語英語
ホスト出版物のタイトルProceedings of the 21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06
ページ1070-1075
ページ数6
出版ステータス出版済み - 2006
外部発表はい
イベント21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06 - Boston, MA, 米国
継続期間: 7月 16 20067月 20 2006

出版物シリーズ

名前Proceedings of the National Conference on Artificial Intelligence
2

その他

その他21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06
国/地域米国
CityBoston, MA
Period7/16/067/20/06

!!!All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • 人工知能

フィンガープリント

「Monte Carlo go has a way to go」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル