Patents by Inventor Silvia Chiappa

Silvia Chiappa 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).

  • GENERATING A MODEL OF A TARGET ENVIRONMENT BASED ON INTERACTIONS OF AN AGENT WITH SOURCE ENVIRONMENTS
    Publication number: 20240126945
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions for an agent in a target environment. In particular, the actions are selected using an environment model for the target environment that is parameterized using interactions of the agent with the target environment and one or more source environments.
    Type: Application
    Filed: October 13, 2023
    Publication date: April 18, 2024
    Inventors: Alexis Bellot, Alan John Malek, Silvia Chiappa
  • Recurrent environment predictors
    Patent number: 11200482
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.
    Type: Grant
    Filed: June 5, 2020
    Date of Patent: December 14, 2021
    Assignee: DeepMind Technologies Limited
    Inventors: Daniel Pieter Wierstra, Shakir Mohamed, Silvia Chiappa, Sebastien Henri Andre Racaniere
  • RECURRENT ENVIRONMENT PREDICTORS
    Publication number: 20200342289
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.
    Type: Application
    Filed: June 5, 2020
    Publication date: October 29, 2020
    Inventors: Daniel Pieter Wierstra, Shakir Mohamed, Silvia Chiappa, Sebastien Henri Andre Racaniere
  • Recurrent environment predictors
    Patent number: 10713559
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.
    Type: Grant
    Filed: May 3, 2019
    Date of Patent: July 14, 2020
    Assignee: DeepMind Technologies Limited
    Inventors: Daniel Pieter Wierstra, Shakir Mohamed, Silvia Chiappa, Sebastien Henri Andre Racaniere
  • RECURRENT ENVIRONMENT PREDICTORS
    Publication number: 20190266475
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for environment simulation. In one aspect, a system comprises a recurrent neural network configured to, at each of a plurality of time steps, receive a preceding action for a preceding time step, update a preceding initial hidden state of the recurrent neural network from the preceding time step using the preceding action, update a preceding cell state of the recurrent neural network from the preceding time step using at least the initial hidden state for the time step, and determine a final hidden state for the time step using the cell state for the time step. The system further comprises a decoder neural network configured to receive the final hidden state for the time step and process the final hidden state to generate a predicted observation characterizing a predicted state of the environment at the time step.
    Type: Application
    Filed: May 3, 2019
    Publication date: August 29, 2019
    Inventors: Daniel Pieter Wierstra, Shakir Mohamed, Silvia Chiappa, Sebastien Henri Andre Racaniere