KI - Künstliche Intelligenz

, Volume 25, Issue 1, pp 43–47 | Cite as

A Parallel General Game Player

  • Jean Méhat
  • Tristan CazenaveEmail author


We have parallelized our general game player Ary on a cluster of computers. We propose multiple parallelization algorithms. For the sake of simplicity all our algorithms have processes that run independently and that join their results at the end of the thinking time in order to choose a move. Parallelization works very well for checkers, quite well for other two player sequential move games and not at all for a few other games.


General game playing UCT search Parallelization 


  1. 1.
    Björnsson Y, Finnsson H (2009) Cadiaplayer: a simulation-based general game player. IEEE Trans Comput Intell AI Games 1(1):4–15 CrossRefGoogle Scholar
  2. 2.
    Cazenave T, Jouandeau N (2007) On the parallelization of UCT. In: Computer games workshop 2007, Amsterdam, The Netherlands, pp 93–101 Google Scholar
  3. 3.
    Cazenave T, Jouandeau N (2008) A parallel Monte-Carlo tree search algorithm. In: Computers and games. Lecture notes in computer science, vol 5131. Springer, Berlin, pp 72–80 CrossRefGoogle Scholar
  4. 4.
    Cazenave T, Saffidine A (2009) Utilisation de la recherche arborescente Monte-Carlo au hex. Rev Intell Artif 23(2–3):183–202 Google Scholar
  5. 5.
    Chaslot G, Winands MHM, van den Herik HJ (2008) Parallel Monte-Carlo tree search. In: Computers and games. Lecture notes in computer science, vol 5131. Springer, Berlin, pp 60–71 CrossRefGoogle Scholar
  6. 6.
    Clune J (2007) Heuristic evaluation functions for general game playing. In: AAAI, pp 1134–1139 Google Scholar
  7. 7.
    Coulom R (2006) Efficient selectivity and back-up operators in Monte-Carlo tree search. In: Computers and games 2006. LNCS, vol 4630. Springer, Berlin, pp 72–83 CrossRefGoogle Scholar
  8. 8.
    Enzenberger M, Müller M (2009) A lock-free multithreaded Monte-Carlo tree search algorithm. In: ACG. Lecture notes in computer science, vol 6048. Springer, Berlin, pp 14–20 Google Scholar
  9. 9.
    Finnsson H, Björnsson Y (2008) Simulation-based approach to general game playing. In: AAAI, pp 259–264 Google Scholar
  10. 10.
    Gelly S, Hoock JB, Rimmel A, Teytaud O, Kalemkarian Y (2008) The parallelization of Monte-Carlo planning—parallelization of mc-planning. In: ICINCO-ICSO, pp 244–249 Google Scholar
  11. 11.
    Gelly S, Silver D (2008) Achieving master level play in 9×9 computer go. In: AAAI, pp 1537–1540 Google Scholar
  12. 12.
    Kato H, Takeuchi I (2008) Parallel Monte-Carlo tree search with simulation servers. In: 13th Game Programming Workshop (GPW-08). Google Scholar
  13. 13.
    Kocsis L, Szepesvàri C (2006) Bandit based Monte-Carlo planning. In: ECML. Lecture notes in computer science, vol 4212. Springer, Berlin, pp 282–293 Google Scholar
  14. 14.
    Love N, Hinrichs T, Genesereth M (2006) General game playing: Game description language specification. Tech. rep, Stanford University Google Scholar
  15. 15.
    Pell B (1994) A strategic metagame player for general chess-like games. In: AAAI, pp 1378–1385 Google Scholar
  16. 16.
    Pitrat J (1968) Realization of a general game-playing program. In: IFIP congress (2), pp 1570–1574 Google Scholar
  17. 17.
    Schiffel S, Thielscher M (2007) Fluxplayer: a successful general game player. In: AAAI, pp 1191–1196 Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.LIASDUniversité Paris 8Saint-Denis CedexFrance
  2. 2.LAMSADEUniversité Paris-DauphineParis Cedex 16France

Personalised recommendations