The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 14, 2024

Filed:

Sep. 27, 2021
Applicant:

Deepmind Technologies Limited, London, GB;

Inventors:

Razvan Pascanu, Letchworth Garden City, GB;

Raia Thais Hadsell, London, GB;

Victor Constant Bapst, London, GB;

Wojciech Czarnecki, London, GB;

James Kirkpatrick, London, GB;

Yee Whye Teh, Oxford, GB;

Nicolas Manfred Otto Heess, London, GB;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2023.01); G06N 3/084 (2023.01); G06N 3/10 (2006.01); G06N 5/043 (2023.01);
U.S. Cl.
CPC ...
G06N 3/084 (2013.01); G06N 3/10 (2013.01); G06N 5/043 (2013.01);
Abstract

A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.


Find Patent Forward Citations

Loading…