Parallel Monte-Carlo Tree Search

  • Guillaume M. J. -B. Chaslot
  • Mark H. M. Winands
  • H. Jaap van den Herik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5131)


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 13×13 Go reveal that in the program Mango root parallelization may lead to the best results for a specific time setting and specific program parameters. However, as soon as the selection mechanism is able to handle more adequately the balance of exploitation and exploration, tree parallelization should have attention too and could become a second choice for parallelizing MCTS. Preliminary experiments on the smaller 9×9 board provide promising prospects for tree parallelization.


Leaf Node Time Setting Board Size Simulated Game Parallelization Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    Computer Go Server (2008),
  3. 3.
    Cazenave, T., Jouandeau, N.: On the parallelization of UCT. In: van den Herik, H.J., Uiterwijk, J.W.H.M., Winands, M.H.M., Schadd, M.P.D. (eds.) Proceedings of the Computer Games Workshop 2007 (CGW 2007), The Netherlands, pp. 93–101. Universiteit Maastricht, Maastricht (2007)Google Scholar
  4. 4.
    Chaslot, G.M.J.-B., Saito, J.-T., Bouzy, B., Uiterwijk, J.W.H.M., van den Herik, H.J.: Monte-Carlo Strategies for Computer Go. In: Schobbens, P.-Y., Vanhoof, W., Schwanen, G. (eds.) Proceedings of the 18th BeNeLux Conference on Artificial Intelligence, pp. 83–90 (2006)Google Scholar
  5. 5.
    Chaslot, G.M.J.-B., Winands, M.H.M., Uiterwijk, J.W.H.M., van den Herik, H.J., Bouzy, B.: Progressive strategies for Monte-Carlo Tree Search. New Mathematics and Natural Computation 4(3), 343–357 (2008)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Coquelin, P.-A., Munos, R.: Bandit algorithms for tree search. In: proceedings of Uncertainty in Artificial Intelligence, Vancouver, Canada (to appear, 2007)Google Scholar
  7. 7.
    Coulom, R.: Efficient selectivity and backup operators in Monte-Carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M(J.) (eds.) CG 2006. LNCS, vol. 4630, pp. 72–83. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Gelly, S., Wang, Y.: Exploration Exploitation in Go: UCT for Monte-Carlo Go. In: Twentieth Annual Conference on Neural Information Processing Systems (NIPS 2006) (2006)Google Scholar
  9. 9.
    Gelly, S., Wang, Y.: Mogo wins 19×19 go tournament. ICGA Journal 30(2), 111–112 (2007)Google Scholar
  10. 10.
    Gelly, S., Wang, Y., Munos, R., Teytaud, O.: Modifications of UCT with Patterns in Monte-Carlo Go. Technical Report 6062, INRIA (2006)Google Scholar
  11. 11.
    Knuth, D.E., Moore, R.W.: An analysis of alpha-beta pruning. Artificial Intelligence 6(4), 293–326 (1975)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Kocsis, L., Szepesvári, C.: Bandit Based Monte-Carlo Planning. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282–293. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Guillaume M. J. -B. Chaslot
    • 1
  • Mark H. M. Winands
    • 1
  • H. Jaap van den Herik
    • 1
  1. 1.Games and AI Group, MICC, Faculty of Humanities and SciencesUniversiteit MaastrichtMaastrichtThe Netherlands

Personalised recommendations