Score Bounded Monte-Carlo Tree Search

被引：0
|
作者：
Cazenave, Tristan [1 ]
Saffidine, Abdallah [1 ]
机构：
[1] Univ Paris 09, LAMSADE, Paris, France
来源：
COMPUTERS AND GAMES | 2011年 / 6515卷
关键词：
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Monte-Carlo Tree Search (MCTS) is a successful algorithm used in many state of the art game engines. We propose to improve a MCTS solver when a game has more than two outcomes. It is for example the case in games that can end in draw positions. In this case it improves significantly a MCTS solver to take into account bounds on the possible scores of a node in order to select the nodes to explore. We apply our algorithm to solving Seki in the game of Go and to Connect Four.
引用
下载
收藏
页码：93 / 104
页数：12
相关论文
共 50 条
  • [21] Parallel Monte-Carlo Tree Search with Simulation Servers
    Kato, Hideki
    Takeuchi, Ikuo
    INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 2010), 2010, : 491 - 498
  • [22] A SHOGI PROGRAM BASED ON MONTE-CARLO TREE SEARCH
    Sato, Yoshikuni
    Takahashi, Daisuke
    Grimbergen, Reijer
    ICGA JOURNAL, 2010, 33 (02) : 80 - 92
  • [23] Generalized Mean Estimation in Monte-Carlo Tree Search
    Dam, Tuan
    Klink, Pascal
    D'Eramo, Carlo
    Peters, Jan
    Pajarinen, Joni
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2397 - 2404
  • [24] Automated Machine Learning with Monte-Carlo Tree Search
    Rakotoarison, Herilalaina
    Schoenauer, Marc
    Sebag, Michele
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3296 - 3303
  • [25] Can Monte-Carlo Tree Search learn to sacrifice?
    Nathan Companez
    Aldeida Aleti
    Journal of Heuristics, 2016, 22 : 783 - 813
  • [26] Monte-Carlo Tree Search Parallelisation for Computer Go
    van Niekerk, Francois
    Kroon, Steve
    van Rooyen, Gert-Jan
    Inggs, Cornelia P.
    PROCEEDINGS OF THE SOUTH AFRICAN INSTITUTE FOR COMPUTER SCIENTISTS AND INFORMATION TECHNOLOGISTS CONFERENCE, 2012, : 129 - 138
  • [27] CROSS-ENTROPY FOR MONTE-CARLO TREE SEARCH
    Chaslot, Guillaume M. J. B.
    Winands, Mark H. M.
    Szita, Istvan
    van den Herik, H. Jaap
    ICGA JOURNAL, 2008, 31 (03) : 145 - 156
  • [28] Monte-Carlo Tree Search for the Game of Scotland Yard
    Nijssen, J. A. M.
    Winands, Mark H. M.
    2011 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG), 2011, : 158 - 165
  • [29] Can Monte-Carlo Tree Search learn to sacrifice?
    Companez, Nathan
    Aleti, Aldeida
    JOURNAL OF HEURISTICS, 2016, 22 (06) : 783 - 813
  • [30] Bayesian Optimization for Backpropagation in Monte-Carlo Tree Search
    Lim, Nengli
    Li, Yueqin
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II, 2021, 12892 : 209 - 221
12345