On the Parallelization of Monte-Carlo planning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

On the Parallelization of Monte-Carlo planning

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.

Domains

Optimization and Control [math.OC]
Fichier principal
Vignette du fichier
icin08.pdf (69.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Olivier Teytaud  : Connect in order to contact the contributor

https://inria.hal.science/inria-00287867

Submitted on : Friday, June 13, 2008-10:56:44 AM

Last modification on : Monday, February 12, 2024-9:48:04 AM

Long-term archiving on: Friday, May 28, 2010-10:19:42 PM

Download

Dates and versions

inria-00287867 , version 1 (13-06-2008)

Identifiers

  • HAL Id : inria-00287867 , version 1

Cite

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 XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

X EC-PARIS CNRS INRIA LIX INSMI X-LIX X-DEP-INFO UMR8623 INRIA2 LRI-AO TDS-MACS UNIV-PARIS-SACLAY
725 View
923 Download

Share

Gmail Facebook X LinkedIn More