Patents by Inventor Praveen Deepak Srinivasan

Praveen Deepak Srinivasan 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).

  • Distributed training of reinforcement learning systems
    Patent number: 11507827
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.
    Type: Grant
    Filed: October 14, 2019
    Date of Patent: November 22, 2022
    Assignee: DeepMind Technologies Limited
    Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
  • DISTRIBUTED TRAINING OF REINFORCEMENT LEARNING SYSTEMS
    Publication number: 20200117992
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.
    Type: Application
    Filed: October 14, 2019
    Publication date: April 16, 2020
    Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
  • Distributed training of reinforcement learning systems
    Patent number: 10445641
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.
    Type: Grant
    Filed: February 4, 2016
    Date of Patent: October 15, 2019
    Assignee: Deepmind Technologies Limited
    Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
  • DISTRIBUTED TRAINING OF REINFORCEMENT LEARNING SYSTEMS
    Publication number: 20160232445
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.
    Type: Application
    Filed: February 4, 2016
    Publication date: August 11, 2016
    Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman