Patents by Inventor Yunan Ye

Yunan Ye 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).

  • State-augmented reinforcement learning
    Patent number: 11880765
    Abstract: A processor training a reinforcement learning model can include receiving a first dataset representing an observable state in reinforcement learning to train a machine to perform an action. The processor receives a second dataset. Using the second dataset, the processor trains a machine learning classifier to make a prediction about an entity related to the action. The processor extracts an embedding from the trained machine learning classifier, and augments the observable state with the embedding to create an augmented state. Based on the augmented state, the processor trains a reinforcement learning model to learn a policy for performing the action, the policy including a mapping from state space to action space.
    Type: Grant
    Filed: October 19, 2020
    Date of Patent: January 23, 2024
    Assignees: International Business Machines Corporation, University of Illinois at Urbana-Champaign
    Inventors: Pin-Yu Chen, Yada Zhu, Jinjun Xiong, Kumar Bhaskaran, Yunan Ye, Bo Li
  • STATE-AUGMENTED REINFORCEMENT LEARNING
    Publication number: 20220121921
    Abstract: A processor training a reinforcement learning model can include receiving a first dataset representing an observable state in reinforcement learning to train a machine to perform an action. The processor receives a second dataset. Using the second dataset, the processor trains a machine learning classifier to make a prediction about an entity related to the action. The processor extracts an embedding from the trained machine learning classifier, and augments the observable state with the embedding to create an augmented state. Based on the augmented state, the processor trains a reinforcement learning model to learn a policy for performing the action, the policy including a mapping from state space to action space.
    Type: Application
    Filed: October 19, 2020
    Publication date: April 21, 2022
    Inventors: Pin-Yu Chen, Yada Zhu, Jinjun Xiong, Kumar Bhaskaran, Yunan Ye, Bo Li