Parallel Monte-Carlo tree search

G. M J B Chaslot, M. H M Winands, H. Jaap van den Herik

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

Abstract

Monte-Carlo Tree Search (MCTS) is a new best-first search method that started a revolution in the field of Computer Go. Parallelizing MCTS is an important way to increase the strength of any Go program. In this article, we discuss three parallelization methods for MCTS: leaf parallelization, root parallelization,and tree parallelization. To be effective tree parallelization requires two techniques: adequately handling of (1) local mutexes and (2) virtual loss. Experiments in 1313 Go reveal that in the program Mango root parallelization may lead to the best results for a specific time setting and specific program parame- ters. However, as soon as the selection mechanism is able to handle more adequately the balance of exploitation and exploration, tree paralleliza- tion should have attention too and could become a second choice for parallelizing MCTS. Preliminary experiments on the smaller 99 board provide promising prospects for tree parallelization.
Original languageEnglish
Title of host publicationComputers and Games
PublisherSpringer
Pages60-71
Number of pages12
ISBN (Print)3540876073
DOIs
Publication statusPublished - 2008

Publication series

SeriesLecture Notes in Computer Science
Volume5131

Cite this

Chaslot, G. M. J. B., Winands, M. H. M., & van den Herik, H. J. (2008). Parallel Monte-Carlo tree search. In Computers and Games (pp. 60-71). Springer. Lecture Notes in Computer Science, Vol.. 5131 https://doi.org/10.1007/978-3-540-87608-3_6