ENVIRONMENT NAVIGATION USING REINFORCEMENT LEARNING

(19)

(11)

EP 3 523 762 B8

(12)	CORRECTED EUROPEAN PATENT SPECIFICATION
	Note: Bibliography reflects the latest situation

(15)	Correction information:
	Corrected version no 1 (W1 B1)

(48)	Corrigendum issued on:
	14.08.2024 Bulletin 2024/33

(45)	Mention of the grant of the patent:
	12.06.2024 Bulletin 2024/24

(21)	Application number: 17812054.9

(22)	Date of filing: 04.11.2017

(51)

International Patent Classification (IPC):

G06N 3/092^(2023.01)
G06N 3/0464^(2023.01)
G06N 3/006^(2023.01)

G06N 3/0442^(2023.01)
G06N 3/084^(2023.01)
G06N 3/045^(2023.01)

(52)	Cooperative Patent Classification (CPC):
	G06N 3/084; G06N 3/006; G06N 3/045; G06N 3/0464; G06N 3/0442; G06N 3/092

(86)	International application number:
	PCT/IB2017/056907

(87)	International publication number:
	WO 2018/083672 (11.05.2018 Gazette 2018/19)

(54)	ENVIRONMENT NAVIGATION USING REINFORCEMENT LEARNING UMWELTNAVIGATION UNTER VERWENDUNG VON VERSTÄRKUNGSLERNEN NAVIGATION D'ENVIRONNEMENT À L'AIDE D'UN APPRENTISSAGE PAR RENFORCEMENT

(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 MK MT NL NO PL PT RO RS SE SI SK SM TR

(30)

Priority:

04.11.2016 US 201662418074 P

(43)	Date of publication of application:
	14.08.2019 Bulletin 2019/33

(60)	Divisional application:
	24173836.8 / 4386624

(73)	Proprietor: DeepMind Technologies Limited
	London EC4A 3TW (GB)

(72)

Inventors:

VIOLA, Fabio
London Greater London N1C 4AG (GB)
MIROWSKI, Piotr Wojciech
London Greater London N1C 4AG (GB)
BANINO, Andrea
London Greater London N1C 4AG (GB)
PASCANU, Razvan
London Greater London N1C 4AG (GB)
SOYER, Hubert Josef
London Greater London N1C 4AG (GB)
BALLARD, Andrew James
London Greater London N1C 4AG (GB)
KUMARAN, Sudarshan
London Greater London N1C 4AG (GB)
HADSELL, Raia Thais
London Greater London N1C 4AG (GB)
SIFRE, Laurent
75009 Paris (FR)
GOROSHIN, Rostislav
London Greater London N1C 4AG (GB)
KAVUKCUOGLU, Koray
London Greater London N1C 4AG (GB)
DENIL, Misha Man Ray
London Greater London N1C 4AG (GB)

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

(56)

References cited: :

GUILLAUME LAMPLE ET AL: "Playing FPS Games with Deep Reinforcement Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 18 September 2016 (2016-09-18), XP080727453
CESAR CADENA ET AL: "Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age", CORR (ARXIV), vol. 1606.05830v2, 20 July 2016 (2016-07-20), pages 1 - 27, XP055448575
VOLODYMYR MNIH ET AL: "Asynchronous Methods for Deep Reinforcement Learning", CORR (ARXIV), vol. 1602.01783v2, 16 June 2016 (2016-06-16), pages 1 - 19, XP055447272
HO K L ET AL: "Loop closure detection in SLAM by combining visual and spatial appearance", ROBOTICS AND AUTONOMOUS SYSTEMS, ELSEVIER SCIENCE PUBLISHERS, AMSTERDAM, NL, vol. 54, no. 9, 30 September 2006 (2006-09-30), pages 740 - 749, XP027954528, ISSN: 0921-8890, [retrieved on 20060930]
TREVOR BARRON ET AL: "Deep Reinforcement Learning in a 3-D Blockworld Environment", WORKSHOP DEEP REINFORCEMENT LEARNING: FRONTIERS AND CHALLENGES, IJCAI 2016, 11 July 2016 (2016-07-11), pages 1 - 6, XP055448052

Note: Within nine months from the publication of the mention of the grant of the European patent, any person may give notice to the European Patent Office of opposition to the European patent granted. Notice of opposition shall be filed in a written reasoned statement. It shall not be deemed to have been filed until the opposition fee has been paid. (Art. 99(1) European Patent Convention).