- 著者
- Hashimoto Junichi Kishimoto Akihiro Yoshizoe Kazuki Ikeda Kokolo
- 出版者
- Springer
- 雑誌
- Lecture Notes in Computer Science (ISSN:03029743)
- 巻号頁・発行日
- vol.7168, pp.1-12, 2012
- 被引用文献数
- 6
Monte-Carlo Tree Search (MCTS) is a very successful approach for improving the performance of game-playing programs. This paper presents the Accelerated UCT algorithm, which overcomes a weakness of MCTS caused by deceptive structures which often appear in game tree search. It consists in using a new backup operator that assigns higher weights to recently visited actions, and lower weights to actions that have not been visited for a long time. Results in Othello, Havannah and Go show that Accelerated UCT is not only more effective than previous approaches but also improves the strength of FUEGO, which is one of the best computer Go programs.
- 著者
- Fujiki Tsubasa Ikeda Kokolo Viennot Simon
- 出版者
- Institute of Electrical and Electronics Engineers (IEEE)
- 雑誌
- 2015 IEEE Conference on Computational Intelligence and Games (CIG)
- 巻号頁・発行日
- pp.407-414, 2015
- 被引用文献数
- 3
A lot of research has been done on classical games such as Chess or Shogi, but not so much on more recent games such as turn-based strategy games, where the players can move multiple pieces at each turn. In this paper, we analyze the game components found in most strategy games, and propose a set of simple rules that could be used as a standard game for research on turn-based strategy games. We have implemented these rules in an open platform, and in the second part of the paper we compare four different Monte-Carlo search algorithms with this platform. Especially, we show the importance of distinguishing and handling differently tactical moves and attacking moves.