Parallel Nested Monte-Carlo Search

Tristan Cazenave (1) , Nicolas Jouandeau (2)

1 LAMSADE - Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision
2 LIASD - Laboratoire d'Informatique Avancée de Saint-Denis

We address the parallelization of a Monte-Carlo search algorithm. On a cluster of 64 cores we obtain a speedup of 56 for the parallelization of Morpion Solitaire. An algorithm that behaves better than a naive one on heterogeneous clusters is also detailed.

Mots clés: Monte-Carlo; Search; Parallelization; Mor- pion Solitaire

Domaines: Intelligence artificielle [cs.AI]

Tristan Cazenave, Nicolas Jouandeau. Parallel Nested Monte-Carlo Search. 12th International Workshop on Nature Inspired Distributed Computing, May 2009, Rome, Italy. ⟨hal-02310192⟩