Scalable distributed Monte-Carlo tree search

Kazuki Yoshizoe, Akihiro Kishimoto, Tomoyuki Kaneko, Haruhiro Yoshimoto, Yutaka Ishikawa

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

22 被引用数 (Scopus)

抄録

Monte-Carlo Tree Search (MCTS) is remarkably successful in two-player games, but parallelizing MCTS has been notoriously difficult to scale well, especially in distributed environments. For a distributed parallel search, transposition-table driven scheduling (TDS) is known to be efficient in several domains. We present a massively parallel MCTS algorithm, that applies the TDS parallelism to the Upper Confidence bound Applied to Trees (UCT) algorithm, which is the most representative MCTS algorithm. To drastically decrease communication overhead, we introduce a reformulation of UCT called Depth-First UCT. The parallel performance of the algorithm is evaluated on clusters using up to 1,200 cores in artificial game-trees. We show that this approach scales well, achieving 740-fold speedups in the best case.

本文言語英語
ホスト出版物のタイトルProceedings of the 4th Annual Symposium on Combinatorial Search, SoCS 2011
ページ180-187
ページ数8
出版ステータス出版済み - 2011
外部発表はい
イベント4th International Symposium on Combinatorial Search, SoCS 2011 - Barcelona, スペイン
継続期間: 7 15 20117 16 2011

出版物シリーズ

名前Proceedings of the 4th Annual Symposium on Combinatorial Search, SoCS 2011

会議

会議4th International Symposium on Combinatorial Search, SoCS 2011
国/地域スペイン
CityBarcelona
Period7/15/117/16/11

All Science Journal Classification (ASJC) codes

  • コンピュータ ネットワークおよび通信

フィンガープリント

「Scalable distributed Monte-Carlo tree search」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル