The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments. Lee, C., Wang, M., Chaslot, Jean-Bernard, G. M., Hoock, J.B., Rimmel, A., Teytaud, O., Tsai, S., Hsu, S., & Hong, T. IEEE Trans. Comp. Intell. AI Games, 1(1):73--89, IEEE, 2009.
The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments [link]Paper  abstract   bibtex   
In order to promote computer Go and stimulate fur- ther development and research in the field, the event activities, Computational Intelligence Forum andWorld 9 9 Computer Go Championship, were held in Taiwan. This study focuses on the in- vited games played in the tournamentTaiwaneseGoPlayersVersus the Computer Program MoGo held at the National University of Tainan (NUTN), Tainan, Taiwan. Several Taiwanese Go players, including one 9-Dan (9D) professional Go player and eight am- ateur Go players, were invited by NUTN to play against MoGo from August 26 to October 4, 2008. The MoGo program combines all-moves-as-first (AMAF)/rapid action value estimation (RAVE) values, online “upper confidence tree (UCT)-like” values, offline values extracted from databases, and expert rules. Additionally, four properties of MoGo are analyzed including: 1) the weakness in corners, 2) the scaling over time, 3) the behavior in handicap games, and 4) the main strength of MoGo in contact fights. The results reveal that MoGo can reach the level of 3 Dan (3D) with: 1) good skills for fights, 2) weaknesses in corners, in particular, for “semeai” situations, and 3) weaknesses in favorable situations such as handicap games. It is hoped that the advances in AI and com- putational power will enable considerable progress in the field of computer Go, with the aim of achieving the same levels as com- puter Chess or Chinese Chess in the future.
@article{ Lee2009,
  abstract = {In order to promote computer Go and stimulate fur- ther development and research in the field, the event activities, Computational Intelligence Forum andWorld 9 9 Computer Go Championship, were held in Taiwan. This study focuses on the in- vited games played in the tournamentTaiwaneseGoPlayersVersus the Computer Program MoGo held at the National University of Tainan (NUTN), Tainan, Taiwan. Several Taiwanese Go players, including one 9-Dan (9D) professional Go player and eight am- ateur Go players, were invited by NUTN to play against MoGo from August 26 to October 4, 2008. The MoGo program combines all-moves-as-first (AMAF)/rapid action value estimation (RAVE) values, online “upper confidence tree (UCT)-like” values, offline values extracted from databases, and expert rules. Additionally, four properties of MoGo are analyzed including: 1) the weakness in corners, 2) the scaling over time, 3) the behavior in handicap games, and 4) the main strength of MoGo in contact fights. The results reveal that MoGo can reach the level of 3 Dan (3D) with: 1) good skills for fights, 2) weaknesses in corners, in particular, for “semeai” situations, and 3) weaknesses in favorable situations such as handicap games. It is hoped that the advances in AI and com- putational power will enable considerable progress in the field of computer Go, with the aim of achieving the same levels as com- puter Chess or Chinese Chess in the future.},
  author = {Lee, Chang-Shing and Wang, Mei-Hui and Chaslot, Guillaume Maurice Jean-Bernard and Hoock, Jean-Baptiste and Rimmel, Arpad and Teytaud, Olivier and Tsai, Shang-Rong and Hsu, Shun-Chin and Hong, Tzung-Pei},
  file = {::},
  issn = {1943-068X},
  journal = {IEEE Trans. Comp. Intell. AI Games},
  keywords = {Computational intelligence,MCTS,MoGo,Monte Carlo tree search,computer Go,game},
  number = {1},
  pages = {73--89},
  publisher = {IEEE},
  title = {{The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments}},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4804732},
  volume = {1},
  year = {2009}
}

Downloads: 0