Patents by Inventor Vinicius Zambaldi

Vinicius Zambaldi 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: 20230196146
    Abstract: A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.
    Type: Application
    Filed: February 13, 2023
    Publication date: June 22, 2023
    Inventors: Yujia Li, Victor Constant Bapst, Vinicius Zambaldi, David Nunes Raposo, Adam Anthony Santoro
  • Publication number: 20230124261
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a spatial embedding neural network that is configured to process data characterizing motion of an agent that is interacting with an environment to generate spatial embeddings. In one aspect, a method comprises: processing data characterizing the motion of the agent in the environment at the current time step using a spatial embedding neural network to generate a current spatial embedding for the current time step; determining a predicted score and a target score for each of a plurality of slots in an external memory, wherein each slot stores: (i) a representation of an observation characterizing a state of the environment, and (ii) a spatial embedding; and determining an update to values of the set of spatial embedding neural network parameters based on an error between the predicted scores and the target scores.
    Type: Application
    Filed: May 12, 2021
    Publication date: April 20, 2023
    Inventors: Benigno Uria-Martínez, Andrea Banino, Borja Ibarz Gabardos, Vinicius Zambaldi, Charles Blundell
  • Patent number: 11580429
    Abstract: A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.
    Type: Grant
    Filed: May 20, 2019
    Date of Patent: February 14, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Yujia Li, Victor Constant Bapst, Vinicius Zambaldi, David Nunes Raposo, Adam Anthony Santoro
  • Publication number: 20210192358
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting the actions of, or influences on, agents in environments with multiple agents, in particular for reinforcement learning. In one aspect, a relational forward model (RFM) system receives agent data representing agent actions for each of multiple agents and implements: an encoder graph neural network subsystem to process the agent data as graph data to provide encoded graph data, a recurrent graph neural network subsystem to process the encoded graph data to provide processed graph data, a decoder graph neural network subsystem to decode the processed graph data to provide decoded graph data and an output to provide representation data for node and/or edge attributes of the decoded graph data relating to a predicted action of one or more of the agents. A reinforcement learning system includes the RFM system.
    Type: Application
    Filed: May 20, 2019
    Publication date: June 24, 2021
    Inventors: Hasuk Song, Andrea Tacchetti, Peter William Battaglia, Vinicius Zambaldi
  • Publication number: 20190354885
    Abstract: A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.
    Type: Application
    Filed: May 20, 2019
    Publication date: November 21, 2019
    Inventors: Yujia Li, Victor Constant Bapst, Vinicius Zambaldi, David Nunes Raposo, Adam Anthony Santoro