Monte-Carlo tree search and rapid action value estimation in computer Go

被引：211
|
作者：
Gelly, Sylvain [2 ]
Silver, David [1 ]
机构：
[1] UCL, London WC1E 6BT, England
[2] Univ Paris 11, LRI, CNRS, INRIA, Orsay, France
来源：
ARTIFICIAL INTELLIGENCE | 2011年 / 175卷 / 11期
关键词：
Computer Go; Monte-Carlo; Search; Reinforcement learning;
D O I：
10.1016/j.artint.2011.03.007
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A new paradigm for search, based on Monte-Carlo simulation, has revolutionised the performance of computer Go programs. In this article we describe two extensions to the Monte-Carlo tree search algorithm, which significantly improve the effectiveness of the basic algorithm. When we applied these two extensions to the Go program MoGo, it became the first program to achieve dan (master) level in 9 x 9 Go. In this article we survey the Monte-Carlo revolution in computer Go, outline the key ideas that led to the success of MoGo and subsequent Go programs, and provide for the first time a comprehensive description, in theory and in practice, of this extended framework for Monte-Carlo tree search. (C) 2011 Elsevier B.V. All rights reserved.
引用
收藏
页码：1856 / 1875
页数：20
相关论文
共 50 条
  • [1] Monte-Carlo Tree Search Parallelisation for Computer Go
    van Niekerk, Francois
    Kroon, Steve
    van Rooyen, Gert-Jan
    Inggs, Cornelia P.
    [J]. PROCEEDINGS OF THE SOUTH AFRICAN INSTITUTE FOR COMPUTER SCIENTISTS AND INFORMATION TECHNOLOGISTS CONFERENCE, 2012, : 129 - 138
  • [2] Application of Monte-Carlo Tree Search in Tsumego of Computer Go
    Wang, Fang
    Peng, Ying
    [J]. MEASUREMENT TECHNOLOGY AND ITS APPLICATION, PTS 1 AND 2, 2013, 239-240 : 1344 - 1347
  • [3] Investigating the Limits of Monte-Carlo Tree Search Methods in Computer Go
    Huang, Shih-Chieh
    Mueller, Martin
    [J]. COMPUTERS AND GAMES, CG 2013, 2014, 8427 : 39 - +
  • [4] Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients
    Lee, Jongmin
    Jeon, Wonseok
    Kim, Geon-Hyeong
    Kim, Kee-Eung
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 4561 - 4568
  • [5] Analyzing Simulations in Monte-Carlo Tree Search for the Game of Go
    Fernando, Sumudu
    Mueller, Martin
    [J]. COMPUTERS AND GAMES, CG 2013, 2014, 8427 : 72 - 83
  • [6] Generalized Mean Estimation in Monte-Carlo Tree Search
    Dam, Tuan
    Klink, Pascal
    D'Eramo, Carlo
    Peters, Jan
    Pajarinen, Joni
    [J]. PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2397 - 2404
  • [7] Monte-Carlo proof-number search for computer Go
    Saito, Jahn-Takeshi
    Chaslot, Guillaume
    Uiterwijk, Jos W. H. M.
    van den Herik, H. Jaap
    [J]. COMPUTERS AND GAMES, 2007, 4630 : 50 - +
  • [8] Time Management for Monte-Carlo Tree Search Applied to the Game of Go
    Huang, Shih-Chieh
    Coulom, Remi
    Lin, Shun-Shii
    [J]. INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 2010), 2010, : 462 - 466
  • [9] Monte-Carlo Tree Search for Logistics
    Edelkamp, Stefan
    Gath, Max
    Greulich, Christoph
    Humann, Malte
    Herzog, Otthein
    Lawo, Michael
    [J]. COMMERCIAL TRANSPORT, 2016, : 427 - 440
  • [10] The Grand Challenge of Computer Go: Monte Carlo Tree Search and Extensions
    Gelly, Sylvain
    Kocsis, Levente
    Schoenauer, Marc
    Sebag, Michele
    Silver, David
    Szepesvari, Csaba
    Teytaud, Olivier
    [J]. COMMUNICATIONS OF THE ACM, 2012, 55 (03) : 106 - 113
12345