Patents by Inventor Robert Dunning

Robert Dunning 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: 12299574
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Grant
    Filed: October 16, 2023
    Date of Patent: May 13, 2025
    Assignee: DeepMind Technologies Limited
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Publication number: 20240220774
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
    Type: Application
    Filed: December 11, 2023
    Publication date: July 4, 2024
    Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
  • Publication number: 20240127060
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Application
    Filed: October 16, 2023
    Publication date: April 18, 2024
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Patent number: 11868894
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Grant
    Filed: January 4, 2023
    Date of Patent: January 9, 2024
    Assignee: DeepMind Technologies Limited
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Patent number: 11842261
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
    Type: Grant
    Filed: December 14, 2020
    Date of Patent: December 12, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
  • Patent number: 11783235
    Abstract: A machine learning system that includes one or more machine learning models implemented in one or more hardware processors, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the one or more machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: October 10, 2023
    Assignee: Hamilton Sundstrand Corporation
    Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
  • Publication number: 20230153617
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Application
    Filed: January 4, 2023
    Publication date: May 18, 2023
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Patent number: 11593646
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Grant
    Filed: February 5, 2019
    Date of Patent: February 28, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Patent number: 11429069
    Abstract: A machine learning system that includes three machine learning models implemented in a hardware processor, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the three machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module is implemented in hardware and receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: August 30, 2022
    Assignee: Hamilton Sundstrand Corporation
    Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
  • Publication number: 20210182737
    Abstract: A machine learning system that includes one or more machine learning models implemented in one or more hardware processors, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the one or more machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.
    Type: Application
    Filed: December 16, 2019
    Publication date: June 17, 2021
    Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
  • Publication number: 20210181694
    Abstract: A machine learning system that includes three machine learning models implemented in a hardware processor, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the three machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module is implemented in hardware and receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.
    Type: Application
    Filed: December 16, 2019
    Publication date: June 17, 2021
    Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
  • Publication number: 20210097373
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
    Type: Application
    Filed: December 14, 2020
    Publication date: April 1, 2021
    Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
  • Publication number: 20210034970
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.
    Type: Application
    Filed: February 5, 2019
    Publication date: February 4, 2021
    Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
  • Patent number: 10872293
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
    Type: Grant
    Filed: May 29, 2019
    Date of Patent: December 22, 2020
    Assignee: DeepMind Technologies Limited
    Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
  • Publication number: 20190370637
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
    Type: Application
    Filed: May 29, 2019
    Publication date: December 5, 2019
    Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
  • Patent number: 8344826
    Abstract: A phased-array antenna filter and diplexer for a super economical broadcast system are provided. The filter and diplexer includes a signal divider tee diplexer, a receive filter and a transmit filter. The diplexer includes a tee branch point, an antenna port, a transmit port and a receive port. The receive filter includes a flat, multi-pole bandpass filter, an input port and an output port, where the input port is coupled to the diplexer receive port to define a receive signal path, from the tee branch point to the receive input port, that has a length of approximately one quarter receive wavelength. The transmit filter includes a folded, multi-pole bandpass filter, an input port and an output port, where the output port is coupled to the diplexer transmit port to define a transmit signal path, from the tee branch point to the transmit output port, that has a length of approximately one quarter transmit wavelength.
    Type: Grant
    Filed: April 21, 2009
    Date of Patent: January 1, 2013
    Assignee: SPX Corporation
    Inventors: Chris Rossiter, Robert Dunning, Torbjorn Johnson
  • Patent number: 8063723
    Abstract: A filter includes a cross-coupling link which includes a crossbar, a first vertical support attached to one end of the crossbar, a second vertical support attached to another end of the crossbar, a first coupling arm attached to the first vertical support, a second coupling arm attached to the second vertical support, a first adjustable support attached to the first coupling arm at one end and grounded at another end, and a second adjustable support attached to the second coupling arm at one end and grounded at another end.
    Type: Grant
    Filed: July 1, 2009
    Date of Patent: November 22, 2011
    Assignee: SPX Corporation
    Inventors: Christopher Rossiter, Robert Dunning
  • Publication number: 20110001583
    Abstract: A filter includes a cross-coupling link which includes a crossbar, a first vertical support attached to one end of the crossbar, a second vertical support attached to another end of the crossbar, a first coupling arm attached to the first vertical support, a second coupling arm attached to the second vertical support, a first adjustable support attached to the first coupling arm at one end and grounded at another end, and a second adjustable support attached to the second coupling arm at one end and grounded at another end.
    Type: Application
    Filed: July 1, 2009
    Publication date: January 6, 2011
    Applicant: SPX Corporation
    Inventors: Christopher Rossiter, Robert Dunning
  • Publication number: 20090284325
    Abstract: A phased-array antenna filter and diplexer for a super economical broadcast system are provided. The filter and diplexer includes a signal divider tee diplexer, a receive filter and a transmit filter. The diplexer includes a tee branch point, an antenna port, a transmit port and a receive port. The receive filter includes a flat, multi-pole bandpass filter, an input port and an output port, where the input port is coupled to the diplexer receive port to define a receive signal path, from the tee branch point to the receive input port, that has a length of approximately one quarter receive wavelength. The transmit filter includes a folded, multi-pole bandpass filter, an input port and an output port, where the output port is coupled to the diplexer transmit port to define a transmit signal path, from the tee branch point to the transmit output port, that has a length of approximately one quarter transmit wavelength.
    Type: Application
    Filed: April 21, 2009
    Publication date: November 19, 2009
    Applicant: SPX Corporation
    Inventors: Chris Rossiter, Torbjorn Johnson, Robert Dunning
  • Patent number: 7559945
    Abstract: A multi-spectra photon therapy device and method of use for providing treatment to a subject in need thereof is described. A multi-spectra photon therapy device comprising an array of LEDs having at least two sets of LEDs configured according to a predetermined pattern, with a first set of LEDs emitting light in the about red wavelength and at least a second set of LEDs emitting light in the about infrared wavelength; a frequency generator for modulating a signal to the LED array; and a controller for selecting the frequency applied to the signal and the duration during which the signal is modulated at the selected frequency; a protocol database including a plurality of predetermined sequences of frequencies and durations of time specific to treat or ameliorate predetermined diseases or conditions.
    Type: Grant
    Filed: January 13, 2006
    Date of Patent: July 14, 2009
    Assignee: Clarimedix Inc.
    Inventors: Harold Richard Breden, Richard Samuel Murdoch, John Robert Dunning, Thomas M. Lopez