Patents by Inventor Sriyash Poddar

Sriyash Poddar 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).

  • Optimal sequential decision making with changing action space
    Patent number: 12111884
    Abstract: Systems and methods for machine learning are described. Embodiments of the present disclosure receive state information that describes a state of a decision making agent in an environment; compute an action vector from an action embedding space based on the state information using a policy neural network of the decision making agent, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and perform an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.
    Type: Grant
    Filed: April 20, 2022
    Date of Patent: October 8, 2024
    Assignee: ADOBE INC.
    Inventors: Tanay Anand, Pinkesh Badjatiya, Sriyash Poddar, Jayakumar Subramanian, Georgios Theocharous, Balaji Krishnamurthy
  • OPTIMAL SEQUENTIAL DECISION MAKING WITH CHANGING ACTION SPACE
    Publication number: 20230342425
    Abstract: Systems and methods for machine learning are described. Embodiments of the present disclosure receive state information that describes a state of a decision making agent in an environment; compute an action vector from an action embedding space based on the state information using a policy neural network of the decision making agent, wherein the policy neural network is trained using reinforcement learning based on a topology loss that constrains changes in a mapping between an action set and the action embedding space; and perform an action that modifies the state of the decision making agent in the environment based on the action vector, wherein the action is selected based on the mapping.
    Type: Application
    Filed: April 20, 2022
    Publication date: October 26, 2023
    Inventors: Tanay Anand, Pinkesh Badjatiya, Sriyash Poddar, Jayakumar Subramanian, Georgios Theocharous, Balaji Krishnamurthy