Enhancements for Multi-Player Monte-Carlo Tree Search

J. A. M. Nijssen; Mark H. M. Winands

doi:10.1007/978-3-642-17928-0_22

Enhancements for Multi-Player Monte-Carlo Tree Search

J. A. M. Nijssen^*, Mark H. M. Winands

^*Corresponding author for this work

Networks and Strategic Optimization

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

Abstract

Monte-carlo tree search (mcts) is becoming increasingly popular for playing multi-player games. In this paper we propose two enhancements for mcts in multi-player games: (1) progressive history and (2) multi-player monte-carlo tree search solver (mp-mcts-solver). We analyze the performance of these enhancements in two different multi-player games: focus and chinese checkers. Based on the experimental results we conclude that progressive history is a considerable improvement in both games and mp-mcts-solver, using the standard update rule, is a genuine improvement in focus.

Original language	English
Title of host publication	Computers and Games
Subtitle of host publication	7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers
Editors	H. Jaap van den Herik, Hiroyuki Iida, Aske Plaat
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	238-249
Number of pages	12
ISBN (Print)	978-3-642-17928-0
DOIs	https://doi.org/10.1007/978-3-642-17928-0_22
Publication status	Published - 2011

Publication series

Series	Lecture Notes in Computer Science
Volume	6515

Access to Document

10.1007/978-3-642-17928-0_22

http://dx.doi.org/10.1007/978-3-642-17928-0_22

Cite this

Nijssen, J. A. M. ; Winands, Mark H. M. / Enhancements for Multi-Player Monte-Carlo Tree Search. Computers and Games: 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers. editor / H. Jaap van den Herik ; Hiroyuki Iida ; Aske Plaat. Berlin, Heidelberg : Springer, 2011. pp. 238-249 (Lecture Notes in Computer Science, Vol. 6515).

@inbook{40861123df614cf881c534cf5710039f,

title = "Enhancements for Multi-Player Monte-Carlo Tree Search",

abstract = "Monte-carlo tree search (mcts) is becoming increasingly popular for playing multi-player games. In this paper we propose two enhancements for mcts in multi-player games: (1) progressive history and (2) multi-player monte-carlo tree search solver (mp-mcts-solver). We analyze the performance of these enhancements in two different multi-player games: focus and chinese checkers. Based on the experimental results we conclude that progressive history is a considerable improvement in both games and mp-mcts-solver, using the standard update rule, is a genuine improvement in focus.",

author = "Nijssen, {J. A. M.} and Winands, {Mark H. M.}",

year = "2011",

doi = "10.1007/978-3-642-17928-0_22",

language = "English",

isbn = "978-3-642-17928-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "238--249",

editor = "{van den Herik}, {H. Jaap} and Hiroyuki Iida and Aske Plaat",

booktitle = "Computers and Games",

address = "United States",

}

Nijssen, JAM & Winands, MHM 2011, Enhancements for Multi-Player Monte-Carlo Tree Search. in HJ van den Herik, H Iida & A Plaat (eds), Computers and Games: 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers. Springer, Berlin, Heidelberg, Lecture Notes in Computer Science, vol. 6515, pp. 238-249. https://doi.org/10.1007/978-3-642-17928-0_22

Enhancements for Multi-Player Monte-Carlo Tree Search. / Nijssen, J. A. M.; Winands, Mark H. M.
Computers and Games: 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers. ed. / H. Jaap van den Herik; Hiroyuki Iida; Aske Plaat. Berlin, Heidelberg: Springer, 2011. p. 238-249 (Lecture Notes in Computer Science, Vol. 6515).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

TY - CHAP

T1 - Enhancements for Multi-Player Monte-Carlo Tree Search

AU - Nijssen, J. A. M.

AU - Winands, Mark H. M.

PY - 2011

Y1 - 2011

N2 - Monte-carlo tree search (mcts) is becoming increasingly popular for playing multi-player games. In this paper we propose two enhancements for mcts in multi-player games: (1) progressive history and (2) multi-player monte-carlo tree search solver (mp-mcts-solver). We analyze the performance of these enhancements in two different multi-player games: focus and chinese checkers. Based on the experimental results we conclude that progressive history is a considerable improvement in both games and mp-mcts-solver, using the standard update rule, is a genuine improvement in focus.

AB - Monte-carlo tree search (mcts) is becoming increasingly popular for playing multi-player games. In this paper we propose two enhancements for mcts in multi-player games: (1) progressive history and (2) multi-player monte-carlo tree search solver (mp-mcts-solver). We analyze the performance of these enhancements in two different multi-player games: focus and chinese checkers. Based on the experimental results we conclude that progressive history is a considerable improvement in both games and mp-mcts-solver, using the standard update rule, is a genuine improvement in focus.

U2 - 10.1007/978-3-642-17928-0_22

DO - 10.1007/978-3-642-17928-0_22

M3 - Chapter

SN - 978-3-642-17928-0

T3 - Lecture Notes in Computer Science

SP - 238

EP - 249

BT - Computers and Games

A2 - van den Herik, H. Jaap

A2 - Iida, Hiroyuki

A2 - Plaat, Aske

PB - Springer

CY - Berlin, Heidelberg

ER -

Nijssen JAM, Winands MHM. Enhancements for Multi-Player Monte-Carlo Tree Search. In van den Herik HJ, Iida H, Plaat A, editors, Computers and Games: 7th International Conference, CG 2010, Kanazawa, Japan, September 24-26, 2010, Revised Selected Papers. Berlin, Heidelberg: Springer. 2011. p. 238-249. (Lecture Notes in Computer Science, Vol. 6515). doi: 10.1007/978-3-642-17928-0_22