LEARNING DOMAIN RANDOMIZATION DISTRIBUTIONS FOR TRANSFER LEARNING

Patent №

US 11,501,167

Granted

2022-11-15

Filed 2020

Owner

THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING/MCGILL UNIVERSITY

+1 more

Lab

AI components

4

ml · speech · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16890981

Method or system for reinforcement learning that simultaneously learns a DR distribution ϕ while optimizing an agent policy Π to maximize performance over the learned DR distribution; method or system for training a learning agent using data synthesized by a simulator based on both a performance of the learning agent and a range of parameters present in the synthesized data.

Machine learningSpeechPlanningAI hardwareG06N 3/08G06N 3/006G06N 3/04G06N 3/0499G06N 3/092G06N 3/096G06N 3/045G06N 7/01

AI classification

Machine learning1.00
Planning1.00
AI hardware1.00
Speech0.76
Vision0.04
Knowledge representation0.03
Natural language0.02
Evolutionary computation0.01

Ownership

THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING/MCGILL UNIVERSITY

assignment · 565430027

HUAWEI TECHNOLOGIES CANADA CO., LTD.

assignment · 565430095

Assignors

AMIRLOO ABOLFATHI, ELMIRA

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC