Patents by Inventor Jean-Bastien François Laurent Grill

Jean-Bastien François Laurent Grill 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).

  • Publication number: 20230083486
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an environment representation neural network of a reinforcement learning system controls an agent to perform a given task. In one aspect, the method includes: receiving a current observation input and a future observation input; generating, from the future observation input, a future latent representation of the future state of the environment; processing, using the environment representation neural network, to generate a current internal representation of the current state of the environment; generating, from the current internal representation, a predicted future latent representation; evaluating an objective function measuring a difference between the future latent representation and the predicted future latent representation; and determining, based on a determined gradient of the objective function, an update to the current values of the environment representation parameters.
    Type: Application
    Filed: February 8, 2021
    Publication date: March 16, 2023
    Inventors: Zhaohan Guo, Mohammad Gheshlaghi Azar, Bernardo Avila Pires, Florent Altché, Jean-Bastien François Laurent Grill, Bilal Piot, Remi Munos
  • Publication number: 20210383225
    Abstract: A computer-implemented method of training a neural network. The method comprises processing a first transformed view of a training data item, e.g. an image, with a target neural network to generate a target output, processing a second transformed view of the training data item, e.g. image, with an online neural network to generate a prediction of the target output, updating parameters of the online neural network to minimize an error between the prediction of the target output and the target output, and updating parameters of the target neural network based on the parameters of the online neural network. The method can effectively train an encoder neural network without using labelled training data items, and without using a contrastive loss, i.e. without needing “negative examples” which comprise transformed views of different data items.
    Type: Application
    Filed: June 4, 2021
    Publication date: December 9, 2021
    Inventors: Jean-Bastien François Laurent Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Remi Munos, Michal Valko