Discovering state-of-the-art reinforcement learning algorithms
J
Junhyuk Oh
G
Gregory Farquhar
I
Iurii Kemaev
D
Dan A. Calian
M
Matteo Hessel
L
Luisa Zintgraf
S
Satinder Singh
H
Hado van Hasselt
D
David Silver
Article Details
Journal
Nature
Volume / Issue
Vol. 648, Issue 8093
Published
December 11, 2025
Pages
312-319
ISSN
0028-0836
Publisher
Nature Portfolio
Authors (9)
J
Junhyuk Oh
G
Gregory Farquhar
I
Iurii Kemaev
D
Dan A. Calian
M
Matteo Hessel
L
Luisa Zintgraf
S
Satinder Singh
H
Hado van Hasselt
D
David Silver
Related Articles from this Journal
Graduating without a thesis: meet the people getting ‘practical’ PhDs in China
Xiaoying You
Jul 2026
10.1038/d41586-026-01242-z
White House rolls out AI funding — and signals a new era for US science
Dan Garisto, Kaia Glickman
Jul 2026
10.1038/d41586-026-02332-8
Personalized gene therapy relieves severe epilepsy in two boys
Jul 2026
10.1038/d41586-026-02267-0
Author Correction: Feature-specific threat coding in lateral septum guides defensive action
Dionnet Leandro Bhatti Mazo, Marc Z. C. Berger et al.
Jul 2026
10.1038/s41586-026-10911-y
Briefing Chat: Baby T. rex were killers from birth, suggest new fossils
Elizabeth Gibney, Nick Petrić Howe
Jul 2026
10.1038/d41586-026-02338-2