Time Management for Monte-Carlo Tree Search Applied to the Game of Go

被引：5

作者：

Huang, Shih-Chieh ^{[1
]}

Coulom, Remi ^{[2
]}

Lin, Shun-Shii ^{[1
]}

机构：

[1] Natl Taiwan Normal Univ, Dept CSIE, Taipei, Taiwan

[2] Univ Lille, INRIA, CNRS, Lille, France

来源：

INTERNATIONAL CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI 2010) | 2010年

关键词：

Monte-Carlo tree search; game of Go; time management;

D O I：

10.1109/TAAI.2010.78

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Monte-Carlo tree search (MCTS) is a new technique that has produced a huge leap forward in the strength of Go-playing programs. An interesting aspect of MCTS that has been rarely studied in the past is the problem of time management. This paper presents the effect on playing strength of a variety of time-management heuristics for 19 x 19 Go. Results indicate that clever time management can have a very significant effect on playing strength. Experiments demonstrate that the most basic algorithm for sudden-death time controls (dividing the remaining time by a constant) produces a winning rate of 43.2 +/- 2.2% against GNU Go 3.8 Level 2, whereas our most efficient time-allocation strategy can reach a winning rate of 60 +/- 2.2% without pondering and 67.4 +/- 2.1% with pondering.

引用

页码：462 / 466

页数：5

共 50 条

[21] Monte-Carlo tree search and rapid action value estimation in computer Go
Gelly, Sylvain
Silver, David
[J]. ARTIFICIAL INTELLIGENCE, 2011, 175 (11) : 1856 - 1875
[22] Monte-Carlo Tree Search Implementation of Fighting Game AIs Having Personas
Ishii, Ryota
Ito, Suguru
Ishihara, Makoto
Harada, Tomohiro
Thawonmas, Ruck
[J]. PROCEEDINGS OF THE 2018 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG'18), 2018, : 54 - 61
[23] Monte-Carlo Tree Search with Tree Shape Control
Marchenko, Oleksandr I.
Marchenko, Oleksii O.
[J]. 2017 IEEE FIRST UKRAINE CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (UKRCON), 2017, : 812 - 817
[24] Monte-Carlo Tree Search: To MC or to DP?
Feldman, Zohar
Domshlak, Carmel
[J]. 21ST EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE (ECAI 2014), 2014, 263 : 321 - 326
[25] Monte-Carlo Tree Search for Constrained POMDPs
Lee, Jongmin
Kim, Geon-Hyeong
Poupart, Pascal
Kim, Kee-Eung
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[26] Monte-Carlo Tree Search in Settlers of Catan
Szita, Istvan
Chaslot, Guillaume
Spronck, Pieter
[J]. ADVANCES IN COMPUTER GAMES, 2010, 6048 : 21 - +
[27] PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
Chaslot, Guillaume M. J-B.
Winands, Mark H. M.
Van den Herik, H. Jaap
Uiterwijk, Jos W. H. M.
Bouzy, Bruno
[J]. NEW MATHEMATICS AND NATURAL COMPUTATION, 2008, 4 (03) : 343 - 357
[28] A Parallel Monte-Carlo Tree Search Algorithm
Cazenave, Tristan
Jouandeau, Nicolas
[J]. COMPUTERS AND GAMES, 2008, 5131 : 72 - 80
[29] Improving Monte-Carlo Tree Search in Havannah
Lorentz, Richard J.
[J]. COMPUTERS AND GAMES, 2011, 6515 : 105 - 115
[30] Score Bounded Monte-Carlo Tree Search
Cazenave, Tristan
Saffidine, Abdallah
[J]. COMPUTERS AND GAMES, 2011, 6515 : 93 - 104

← 1 2 3 4 5 →