Patents by Inventor Pararth Shah

Pararth Shah 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: 11941504
    Abstract: Implementations relate to using deep reinforcement learning to train a model that can be utilized, at each of a plurality of time steps, to determine a corresponding robotic action for completing a robotic task. Implementations additionally or alternatively relate to utilization of such a model in controlling a robot. The robotic action determined at a given time step utilizing such a model can be based on: current sensor data associated with the robot for the given time step, and free-form natural language input provided by a user. The free-form natural language input can direct the robot to accomplish a particular task, optionally with reference to one or more intermediary steps for accomplishing the particular task. For example, the free-form natural language input can direct the robot to navigate to a particular landmark, with reference to one or more intermediary landmarks to be encountered in navigating to the particular landmark.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: March 26, 2024
    Assignee: GOOGLE LLC
    Inventors: Pararth Shah, Dilek Hakkani-Tur, Juliana Kew, Marek Fiser, Aleksandra Faust
  • Publication number: 20210086353
    Abstract: Implementations relate to using deep reinforcement learning to train a model that can be utilized, at each of a plurality of time steps, to determine a corresponding robotic action for completing a robotic task. Implementations additionally or alternatively relate to utilization of such a model in controlling a robot. The robotic action determined at a given time step utilizing such a model can be based on: current sensor data associated with the robot for the given time step, and free-form natural language input provided by a user. The free-form natural language input can direct the robot to accomplish a particular task, optionally with reference to one or more intermediary steps for accomplishing the particular task. For example, the free-form natural language input can direct the robot to navigate to a particular landmark, with reference to one or more intermediary landmarks to be encountered in navigating to the particular landmark.
    Type: Application
    Filed: March 22, 2019
    Publication date: March 25, 2021
    Inventors: Pararth Shah, Dilek Hakkani-Tur, Juliana Kew, Marek Fiser, Aleksandra Faust
  • Patent number: 10424302
    Abstract: Techniques are described related to turn-based reinforcement learning for dialog management. In various implementations, dialog states and corresponding responsive actions generated during a multi-turn human-to-computer dialog session may be obtained. A plurality of turn-level training instances may be generated, each including: a given dialog state of the plurality of dialog states at an outset of a given turn of the human-to-computer dialog session; and a given responsive action that was selected based on the given dialog state. One or more of the turn-level training instances may further include a turn-level feedback value that reflects on the given responsive action selected during the given turn. A reward value may be generated based on an outcome of the human-to-computer dialog session. The dialog management policy model may be trained based on turn-level feedback values of the turn-level training instance(s) and the reward value.
    Type: Grant
    Filed: October 12, 2017
    Date of Patent: September 24, 2019
    Assignee: GOOGLE LLC
    Inventors: Pararth Shah, Larry Paul Heck, Dilek Hakkani-Tur
  • Publication number: 20190115027
    Abstract: Techniques are described related to turn-based reinforcement learning for dialog management. In various implementations, dialog states and corresponding responsive actions generated during a multi-turn human-to-computer dialog session may be obtained. A plurality of turn-level training instances may be generated, each including: a given dialog state of the plurality of dialog states at an outset of a given turn of the human-to-computer dialog session; and a given responsive action that was selected based on the given dialog state. One or more of the turn-level training instances may further include a turn-level feedback value that reflects on the given responsive action selected during the given turn. A reward value may be generated based on an outcome of the human-to-computer dialog session. The dialog management policy model may be trained based on turn-level feedback values of the turn-level training instance(s) and the reward value.
    Type: Application
    Filed: October 12, 2017
    Publication date: April 18, 2019
    Inventors: Pararth Shah, Larry Paul Heck, Dilek Hakkani-Tur