(19)
(11) EP 4 569 439 A1

(12)

(43) Date of publication:
18.06.2025 Bulletin 2025/25

(21) Application number: 23772248.3

(22) Date of filing: 15.09.2023
(51) International Patent Classification (IPC): 
G06N 3/006(2023.01)
G06N 3/092(2023.01)
G06N 3/0464(2023.01)
G06N 3/0985(2023.01)
G06N 3/045(2023.01)
G06N 3/096(2023.01)
G06N 3/084(2023.01)
(52) Cooperative Patent Classification (CPC):
G06N 3/006; G06N 3/045; G06N 3/0985; G06N 3/096; G06N 3/092; G06N 3/0464; G06N 3/084
(86) International application number:
PCT/EP2023/075512
(87) International publication number:
WO 2024/056891 (21.03.2024 Gazette 2024/12)
(84) Designated Contracting States:
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated Extension States:
BA
Designated Validation States:
KH MA MD TN

(30) Priority: 15.09.2022 US 202263407132 P

(71) Applicant: DeepMind Technologies Limited
London EC4A 3TW (GB)

(72) Inventors:
  • JIANG, Ray
    London N1C 4AG (GB)
  • PUIGDOMÈNECH BADIA, Adrià
    London N1C 4AG (GB)
  • CAMPOS CAMÚÑEZ, Víctor
    London N1C 4AG (GB)
  • KAPTUROWSKI, Steven James
    London N1C 4AG (GB)
  • RAKICEVIC, Nemanja
    London N1C 4AG (GB)

(74) Representative: Marks & Clerk GST 
1 New York Street
Manchester M1 4HD
Manchester M1 4HD (GB)

   


(54) DATA-EFFICIENT REINFORCEMENT LEARNING WITH ADAPTIVE RETURN COMPUTATION SCHEMES