Art

J-GLOBAL ID：201602221222580548   Reference number：16A0172982

Mastering the game of Go with deep neural networks and tree search

ディープニューラルネットワークと木探索を用いた囲碁の習得

Author (20)： SILVER David (Google DeepMind, London, GBR) ,  HUANG Aja (Google DeepMind, London, GBR) ,  MADDISON Chris J. (Google DeepMind, London, GBR) ,  GUEZ Arthur (Google DeepMind, London, GBR) ,  SIFRE Laurent (Google DeepMind, London, GBR) ,  VAN DEN DRIESSCHE George (Google DeepMind, London, GBR) ,  SCHRITTWIESER Julian (Google DeepMind, London, GBR) ,  ANTONOGLOU Ioannis (Google DeepMind, London, GBR) ,  PANNEERSHELVAM Veda (Google DeepMind, London, GBR) ,  LANCTOT Marc (Google DeepMind, London, GBR) ,  DIELEMAN Sander (Google DeepMind, London, GBR) ,  GREWE Dominik (Google DeepMind, London, GBR) ,  KALCHBRENNER Nal (Google DeepMind, London, GBR) ,  LILLICRAP Timothy (Google DeepMind, London, GBR) ,  LEACH Madeleine (Google DeepMind, London, GBR) ,  KAVUKCUOGLU Koray (Google DeepMind, London, GBR) ,  GRAEPEL Thore (Google DeepMind, London, GBR) ,  HASSABIS Demis (Google DeepMind, London, GBR) ,  NHAM John (Google, California, USA) ,  SUTSKEVER Ilya (Google, California, USA)
Material： Nature (London)  (Nature (Lond))
Volume： 529  Issue： 7587  Page： 484-489  Publication year： Jan. 28, 2016 
JST Material Number： D0193B  ISSN： 0028-0836  Document type： Article
Article type： 原著論文  Country of issue： United Kingdom (GBR)  Language： ENGLISH (EN)

Thesaurus term： *neural network(biomodel) ,  *tree search ,  *artificial intelligence ,  pleasure ,  *two-person game ,  supervised learning ,  reinforcement learning ,  Monte Carlo method ,  computer program ,  performance evaluation ,  algorithm ,  gaming simulation
Semi thesaurus term： deep neural network ,  computer Igo ,  Monte-Carlo tree search ,  Monte Carlo simulation ,  search algorithm

JST classification (2)： Artificial intelligence  (JE08000Z) ,  Game thoery  (KA03060T)

Terms in the title (4)： ディープニューラルネットワーク ,  木探索 ,  囲碁 ,  習得