中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.013 seconds)

    SIMULATION MODELING EXCHANGE
    2.
    发明申请
    SIMULATION MODELING EXCHANGE 审中-公开

    公开(公告)号：US20200167687A1

    公开(公告)日：2020-05-28

    申请号：US16201864

    申请日：2018-11-27

    Applicant: Amazon Technologies, Inc.

    Inventor： Sahika Genc ,  Sunil Mallya Kasaragod ,  Leo Parker Dirac ,  Bharathan Balaji ,  Saurabh Gupta

    IPC: G06N20/00 ,  G06F17/50 ,  B25J9/16

    Abstract: A simulation application container executes a simulation of a system in a simulation environment, through which an agent representing the system uses a reinforcement learning model to operate within the simulation environment. The simulation application container obtains data indicating how the agent performed in the simulation environment and transmits this data to a robot application container. The robot application container uses the data to update the reinforcement learning model and provides the updated reinforcement learning model to perform another iteration of the simulation and continue training the reinforcement learning model.

    Integrated machine learning training
    3.
    发明授权
    Integrated machine learning training 有权

    公开(公告)号：US12118456B1

    公开(公告)日：2024-10-15

    申请号：US16198730

    申请日：2018-11-21

    Applicant: Amazon Technologies, Inc.

    Inventor： Sahika Genc ,  Bharathan Balaji ,  Urvashi Chowdhary ,  Leo Parker Dirac ,  Saurabh Gupta ,  Vineet Khare ,  Sunil Mallya Kasaragod

    IPC: G06N3/08 ,  G06F30/20

    CPC classification number: G06N3/08 ,  G06F30/20

    Abstract: A machine learning environment utilizing training data generated by customer networks. A reinforcement learning machine learning environment receives and processes training data generated by simulated hosted, or integrated, customer networks. The reinforcement learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the integrated customer networks. The customer networks include an agent process that collects training data and forwards the training data to the machine learning clusters. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configure the application of the reinforcement learning machine learning processes.

    Decoupled machine learning training
    4.
    发明授权
    Decoupled machine learning training 有权

    公开(公告)号：US11861490B1

    公开(公告)日：2024-01-02

    申请号：US16198726

    申请日：2018-11-21

    Applicant: Amazon Technologies, Inc.

    Inventor： Saurabh Gupta ,  Bharathan Balaji ,  Leo Parker Dirac ,  Sahika Genc ,  Vineet Khare ,  Ragav Venkatesan ,  Gurumurthy Swaminathan

    IPC: G06N3/08 ,  G06N3/04 ,  G06F18/214 ,  G06F18/21

    CPC classification number: G06N3/08 ,  G06F18/214 ,  G06F18/2178 ,  G06N3/04

    Abstract: A machine learning environment utilizing training data generated by customer environments. A reinforced learning machine learning environment receives and processes training data generated by independently hosted, or decoupled, customer environments. The reinforced learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the decoupled customer environments. The customer environments include an agent process that collects training data and forwards the training data to the machine learning clusters without exposing the customer environment. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configured the application of the reinforced learning machine learning processes.

Patent Agency Ranking