Multilabeled Value Networks for Computer Go
檔案
本條目沒有附加檔案。
日期
2018-12-01
類型
系所
期刊名稱
IEEE TRANSACTIONS ON GAMES
卷期與頁次
第 10 卷,頁 378–389
ISSN
2475-1502
語言
英文
摘要
This paper proposes a new approach to a novel value network architecture for the game Go, called a multilabeled (ML) value network. In the ML value network, different values (win rates) are trained simultaneously for different settings of komi, a compensation given to balance the initiative of playing first. The ML value network has three advantages: 1) it outputs values for different komi; (2) it supports dynamic komi; and (3) it lowers the mean squared error (MSE). This paper also proposes a new dynamic komi method to improve game-playing strength. This paper also performs experiments to demonstrate the merits of the architecture. First, the MSE of the ML value network is generally lower than the value network alone. Second, the program based on the ML value network wins by a rate of 67.6% against the program based on the value network alone. Third, the program with the proposed dynamic komi method significantly improves the playing strength over the baseline that does not use dynamic komi, especially for handicap games. To our knowledge, up to date, no handicap games have been played openly by programs using value networks. This paper provides these programs with a useful approach to playing handicap games.
關鍵詞
Board evaluation (BV)Computer Godynamic komipolicy networkreinforcement learningsupervised learningvalue network所屬典藏
期刊論文引用此條目
Wu, T.-R., Wu, I.-C., Chen, G.-W., Wei, T.-H., Wu, H.-C., Lai, T.-Y., & Lan, L.-C. (2018). Multilabeled Value Networks for Computer Go. IEEE TRANSACTIONS ON GAMES, 10, 378–389. https://doi.org/10.1109/TG.2018.2852806
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/148616