Patents by Inventor Melissa MOZIFIAN

Melissa MOZIFIAN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Learning domain randomization distributions for transfer learning
    Patent number: 11501167
    Abstract: Method or system for reinforcement learning that simultaneously learns a DR distribution ? while optimizing an agent policy ? 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.
    Type: Grant
    Filed: June 2, 2020
    Date of Patent: November 15, 2022
    Assignees: HUAWEI TECHNOLOGIES CANADA CO., LTD., THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING/MCGILL UNIVERSITY
    Inventors: Juan Camilo Gamboa Higuera, Melissa Mozifian, David Meger, Elmira Amirloo Abolfathi
  • LEARNING DOMAIN RANDOMIZATION DISTRIBUTIONS FOR TRANSFER LEARNING
    Publication number: 20210097386
    Abstract: Method or system for reinforcement learning that simultaneously learns a DR distribution ? while optimizing an agent policy ? 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.
    Type: Application
    Filed: June 2, 2020
    Publication date: April 1, 2021
    Inventors: Juan CAMILO GAMBOA HIGUERA, Melissa MOZIFIAN, David MEGER, Elmira AMIRLOO ABOLFATHI