Skip to Main content Skip to Navigation
Conference papers

On the Parallelization of Monte-Carlo planning

Sylvain Gelly 1, 2 Jean-Baptiste Hoock 3 Arpad Rimmel 3 Olivier Teytaud 1, 2 Yann Kalemkarian 4
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
2 LRI - Laboratoire de Recherche en Informatique
3 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
4 Bull - Bull SAS
Abstract : We provide a parallelization with and without shared-memory for Bandit-Based Monte-Carlo Planning algorithms, applied to the game of Go. The resulting algorithm won the first non-blitz game against a professionnal human player in 9x9 Go.
keyword : Parallelization Monte-Carlo Planning Bandits
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download
https://hal.inria.fr/inria-00287867
Contributor : Olivier Teytaud <>
Submitted on : Friday, June 13, 2008 - 10:56:44 AM
Last modification on : Friday, May 1, 2020 - 1:43:57 AM
Document(s) archivé(s) le : Friday, May 28, 2010 - 10:19:42 PM

File

Vignette du document
icin08.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00287867, version 1

Collections

CNRS | INRIA | INSMI | UMR8623 | LRI-AO | X | LIX | X-LIX | TDS-MACS | X-DEP-INFO

Citation

Sylvain Gelly, Jean-Baptiste Hoock, Arpad Rimmel, Olivier Teytaud, Yann Kalemkarian. On the Parallelization of Monte-Carlo planning. ICINCO, May 2008, Madeira, Portugal. ⟨inria-00287867⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

1283

Files downloads

826

 

Contact                    Legal Notice                    Personal Data