標題: Multilabeled Value Networks for Computer Go
作者: Wu, Ti-Rong
Wu, I-Chen
Chen, Guan-Wun
Wei, Ting-Han
Wu, Hung-Chun
Lai, Tung-Yi
Lan, Li-Cheng
資訊工程學系
Department of Computer Science
關鍵字: Board evaluation (BV);Computer Go;dynamic komi;policy network;reinforcement learning;supervised learning;value network
公開日期: 1-Dec-2018
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.
URI: http://dx.doi.org/10.1109/TG.2018.2852806
http://hdl.handle.net/11536/148616
ISSN: 2475-1502
DOI: 10.1109/TG.2018.2852806
期刊: IEEE TRANSACTIONS ON GAMES
Volume: 10
起始頁: 378
結束頁: 389
Appears in Collections:Articles