Sciweavers

Share
CG
2010
Springer

Scalability and Parallelization of Monte-Carlo Tree Search

8 years 5 months ago
Scalability and Parallelization of Monte-Carlo Tree Search
Monte-Carlo Tree Search is now a well established algorithm, in games and beyond. We analyze its scalability, and in particular its limitations, and the implications in terms of parallelization, in particular for our program MoGo but also for our Havannah program Shakti. In particular, we get a good efficiency for the parallel versions, both for multicore machines and for message-passing machines, but in spite of promising results in self-play there are situations for which increasing the time per move does not solve anything, and therefore parallelization is not the solution either. Nonetheless, for problems on which the Monte-Carlo part is less biased than in Go, parallelization should be very efficient even without shared memory.
Amine Bourki, Guillaume Chaslot, Matthieu Coulm, V
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where CG
Authors Amine Bourki, Guillaume Chaslot, Matthieu Coulm, Vincent Danjean, Hassen Doghmen, Jean-Baptiste Hoock, Thomas Hérault, Arpad Rimmel, Fabien Teytaud, Olivier Teytaud, Paul Vayssière, Ziqin Yut
Comments (0)
books