Multilabeled value networks for computer go

Ti Rong Wu, I. Chen Wu*, Guan Wun Chen, Ting Han Wei, Hung Chun Wu, Tung Yi Lai, Li Cheng Lan

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

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. 2017 IEEE.

Original languageEnglish
Article number8403305
Pages (from-to)378-389
Number of pages12
JournalIEEE Transactions on Games
Volume10
Issue number4
DOIs
StatePublished - Dec 2018

Keywords

  • Board evaluation (BV)
  • Computer Go
  • Dynamic komi
  • Policy network
  • Reinforcement learning
  • Supervised learning
  • Value network

Fingerprint Dive into the research topics of 'Multilabeled value networks for computer go'. Together they form a unique fingerprint.

Cite this