文献
J-GLOBAL ID:201502243056189083
整理番号:15A0341870
深層強化学習を介した人間レベルの制御
Human-level control through deep reinforcement learning
著者 (19件):
MNIH Volodymyr
(Google DeepMind, London, GBR)
,
KAVUKCUOGLU Koray
(Google DeepMind, London, GBR)
,
SILVER David
(Google DeepMind, London, GBR)
,
RUSU Andrei A.
(Google DeepMind, London, GBR)
,
VENESS Joel
(Google DeepMind, London, GBR)
,
BELLEMARE Marc G.
(Google DeepMind, London, GBR)
,
GRAVES Alex
(Google DeepMind, London, GBR)
,
RIEDMILLER Martin
(Google DeepMind, London, GBR)
,
FIDJELAND Andreas K.
(Google DeepMind, London, GBR)
,
OSTROVSKI Georg
(Google DeepMind, London, GBR)
,
PETERSEN Stig
(Google DeepMind, London, GBR)
,
BEATTIE Charles
(Google DeepMind, London, GBR)
,
SADIK Amir
(Google DeepMind, London, GBR)
,
ANTONOGLOU Ioannis
(Google DeepMind, London, GBR)
,
KING Helen
(Google DeepMind, London, GBR)
,
KUMARAN Dharshan
(Google DeepMind, London, GBR)
,
WIERSTRA Daan
(Google DeepMind, London, GBR)
,
LEGG Shane
(Google DeepMind, London, GBR)
,
HASSABIS Demis
(Google DeepMind, London, GBR)
資料名:
Nature (London)
(Nature (London))
巻:
518
号:
7540
ページ:
529-533
発行年:
2015年02月26日
JST資料番号:
D0193B
ISSN:
0028-0836
資料種別:
逐次刊行物 (A)
記事区分:
短報
発行国:
イギリス (GBR)
言語:
英語 (EN)