EP3701432 - DISTRIBUTIONAL REINFORCEMENT LEARNING USING QUANTILE FUNCTION NEURAL NETWORKS [Right-click to bookmark this link] | Status | Grant of patent is intended Status updated on 07.05.2024 Database last updated on 03.09.2024 | |
Former | Examination is in progress Status updated on 27.01.2023 | ||
Former | Request for examination was made Status updated on 31.07.2020 | ||
Former | The international publication has been made Status updated on 17.08.2019 | ||
Former | unknown Status updated on 26.02.2019 | Most recent event Tooltip | 07.05.2024 | New entry: Communication of intention to grant a patent | Applicant(s) | For all designated states DeepMind Technologies Limited 5 New Street Square London EC4A 3TW / GB | [N/P] |
Former [2020/36] | For all designated states DeepMind Technologies Limited 5 New Street Square London EC4A 3TW / GB | Inventor(s) | 01 /
OSTROVSKI, Georg 6 Pancras Square London N1C 4AG / GB | 02 /
DABNEY, William Clinton 6 Pancras Square London N1C 4AG / GB | [2020/36] | Representative(s) | Marks & Clerk GST 1 New York Street Manchester M1 4HD / GB | [N/P] |
Former [2020/36] | Suckling, Andrew Michael Marks & Clerk LLP Fletcher House The Oxford Science Park Heatley Road Oxford OX4 4GE / GB | Application number, filing date | 19704796.2 | 11.02.2019 | [2020/36] | WO2019EP53315 | Priority number, date | US201862628875P | 09.02.2018 Original published format: US 201862628875 P | US201862646154P | 21.03.2018 Original published format: US 201862646154 P | [2020/36] | Filing language | EN | Procedural language | EN | Publication | Type: | A1 Application with search report | No.: | WO2019155061 | Date: | 15.08.2019 | Language: | EN | [2019/33] | Type: | A1 Application with search report | No.: | EP3701432 | Date: | 02.09.2020 | Language: | EN | The application published by WIPO in one of the EPO official languages on 15.08.2019 takes the place of the publication of the European patent application. | [2020/36] | Search report(s) | International search report - published on: | EP | 15.08.2019 | Classification | IPC: | G06N3/092, G06N3/047, // G06N3/084, G06N7/01 | [2024/21] | CPC: |
G06N3/047 (EP);
G06N3/08 (US);
G06N3/04 (US);
G06N3/092 (EP);
G06N3/084 (EP);
G06N7/01 (EP)
|
Former IPC [2020/36] | G06N3/04, G06N3/08 | 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 [2020/36] | Title | German: | VERTEILTES VERSTÄRKUNGSLERNEN UNTER VERWENDUNG VON NEURONALEN NETZEN MIT QUANTILFUNKTION | [2020/36] | English: | DISTRIBUTIONAL REINFORCEMENT LEARNING USING QUANTILE FUNCTION NEURAL NETWORKS | [2020/36] | French: | APPRENTISSAGE DE RENFORCEMENT DISTRIBUTIONNEL À L'AIDE DE RÉSEAUX NEURONAUX DE FONCTION QUANTILE | [2020/36] | Entry into regional phase | 28.05.2020 | National basic fee paid | 28.05.2020 | Designation fee(s) paid | 28.05.2020 | Examination fee paid | Examination procedure | 28.05.2020 | Examination requested [2020/36] | 28.05.2020 | Date on which the examining division has become responsible | 18.12.2020 | Amendment by applicant (claims and/or description) | 27.01.2023 | Despatch of a communication from the examining division (Time limit: M06) | 10.07.2023 | Reply to a communication from the examining division | 22.03.2024 | Cancellation of oral proceeding that was planned for 16.04.2024 | 16.04.2024 | Date of oral proceedings (cancelled) | 08.05.2024 | Communication of intention to grant the patent | Fees paid | Renewal fee | 25.02.2021 | Renewal fee patent year 03 | 24.02.2022 | Renewal fee patent year 04 | 23.02.2023 | Renewal fee patent year 05 | 26.02.2024 | Renewal fee patent year 06 |
Opt-out from the exclusive Tooltip competence of the Unified Patent Court | See the Register of the Unified Patent Court for opt-out data | ||
Responsibility for the accuracy, completeness or quality of the data displayed under the link provided lies entirely with the Unified Patent Court. | Documents cited: | Search | [A]CN106094516 (NANJING UNIVERSITY OF TECHNOLOGY ) [A] 1-15 * abstract; figures 1-5 ** paragraph [0001] - paragraph [00039] *; | [A]US2017076201 (VAN HASSELT HADO PHILIP [GB], et al) [A] 1-15 * abstract; figures 1,3 * * paragraph [0001] - paragraph [0006] * * paragraph [0012] - paragraph [0053] *; | [A]WO2017091629 (OSARO INC [US]) [A] 1-15 * abstract; figures 1,4,5 * * page 1, line 1 - page 4, line 16 * * page 5, line 1 - page 19, line 4 *; | [XI] - WILL DABNEY ET AL, "Distributional Reinforcement Learning with Quantile Regression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20171027), XP080832261 [X] 1-4,7-15 * abstract; figures 1,2,3,4 * * page 1, column l, line 1 - page 13, column r, line l * [I] 5-6 | [PX] - WILL DABNEY ET AL, "Implicit Quantile Networks for Distributional Reinforcement Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20180614), XP080891965 [PX] 1-15 * abstract; figures 1,2,3,4 * * page 1, column l, line 1 - page 13, column r, line l * | [A] - AUDRUNAS GRUSLYS ET AL, "The Reactor: A Sample-Efficient Actor-Critic Architecture", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20170415), XP080763199 [A] 1-15 * abstract; figures 1-6 * * page 1, column l, line 1 - page 9, column l, line l * | [A] - MATTEO HESSEL ET AL, "Rainbow: Combining Improvements in Deep Reinforcement Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20171006), XP080826589 [A] 1-15 * abstract; figures 1,4 * * page 1, column l, line 1 - page 8, column l, line 4 * | [A] - Anonymous, "DISTRIBUTIONAL POLICY GRADIENTS", (20180125), pages 1 - 16, URL: https://openreview.net/references/pdf?id=Hk9FaMZCW, (20190426), XP055583901 [A] 1-15 * abstract; figures 1,4 * * page 1, line 1 - page 9, line l * | International search | [A]CN106094516 (NANJING UNIVERSITY OF TECHNOLOGY ) [A] 1-15 * abstract; figures 1-5 ** paragraph [0001] - paragraph [00039] *; | [A]US2017076201 (VAN HASSELT HADO PHILIP [GB], et al) [A] 1-15 * abstract; figures 1,3 * * paragraph [0001] - paragraph [0006] * * paragraph [0012] - paragraph [0053] *; | [A]WO2017091629 (OSARO INC [US]) [A] 1-15 * abstract; figures 1,4,5 * * page 1, line 1 - page 4, line 16 * * page 5, line 1 - page 19, line 4 *; | [XI] - WILL DABNEY ET AL, "Distributional Reinforcement Learning with Quantile Regression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20171027), XP080832261 [X] 1-4,7-15 * abstract; figures 1,2,3,4 * * page 1, column l, line 1 - page 13, column r, line l * [I] 5,6 | [XP] - WILL DABNEY ET AL, "Implicit Quantile Networks for Distributional Reinforcement Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20180614), XP080891965 [XP] 1-15 * abstract; figures 1,2,3,4 * * page 1, column l, line 1 - page 13, column r, line l * | [A] - AUDRUNAS GRUSLYS ET AL, "The Reactor: A Sample-Efficient Actor-Critic Architecture", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20170415), XP080763199 [A] 1-15 * abstract; figures 1-6 * * page 1, column l, line 1 - page 9, column l, line l * | [A] - MATTEO HESSEL ET AL, "Rainbow: Combining Improvements in Deep Reinforcement Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, (20171006), XP080826589 [A] 1-15 * abstract; figures 1,4 * * page 1, column l, line 1 - page 8, column l, line 4 * | [A] - Anonymous, "DISTRIBUTIONAL POLICY GRADIENTS", (20180125), pages 1 - 16, URL: https://openreview.net/references/pdf?id=Hk9FaMZCW, (20190426), XP055583901 [A] 1-15 * abstract; figures 1,4 * * page 1, line 1 - page 9, line l * |