Patents by Inventor David Paul Reichert

David Paul Reichert 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).

  • Patent number: 11328183
    Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.
    Type: Grant
    Filed: September 14, 2020
    Date of Patent: May 10, 2022
    Assignee: DeepMind Technologies Limited
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Publication number: 20210089834
    Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.
    Type: Application
    Filed: December 7, 2020
    Publication date: March 25, 2021
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Publication number: 20210073594
    Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.
    Type: Application
    Filed: September 14, 2020
    Publication date: March 11, 2021
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Patent number: 10860895
    Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.
    Type: Grant
    Filed: November 19, 2019
    Date of Patent: December 8, 2020
    Assignee: DeepMind Technologies Limited
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Patent number: 10776670
    Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.
    Type: Grant
    Filed: November 19, 2019
    Date of Patent: September 15, 2020
    Assignee: DeepMind Technologies Limited
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Publication number: 20200090006
    Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.
    Type: Application
    Filed: November 19, 2019
    Publication date: March 19, 2020
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
  • Publication number: 20200082227
    Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.
    Type: Application
    Filed: November 19, 2019
    Publication date: March 12, 2020
    Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere