中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

80 records (took 0.025 seconds)

    Training action selection neural networks using look-ahead search
    3.
    发明授权
    Training action selection neural networks using look-ahead search 有权

    公开(公告)号：US12147899B2

    公开(公告)日：2024-11-19

    申请号：US18528640

    申请日：2023-12-04

    Applicant: DeepMind Technologies Limited

    Inventor： Karen Simonyan ,  David Silver ,  Julian Schrittwieser

    IPC: G06N3/08 ,  G06N7/01

    Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network. One of the methods includes receiving an observation characterizing a current state of the environment; determining a target network output for the observation by performing a look ahead search of possible future states of the environment starting from the current state until the environment reaches a possible future state that satisfies one or more termination criteria, wherein the look ahead search is guided by the neural network in accordance with current values of the network parameters; selecting an action to be performed by the agent in response to the observation using the target network output generated by performing the look ahead search; and storing, in an exploration history data store, the target network output in association with the observation for use in updating the current values of the network parameters.

    TRAINING ACTION SELECTION NEURAL NETWORKS USING LOOK-AHEAD SEARCH
    4.
    发明公开
    TRAINING ACTION SELECTION NEURAL NETWORKS USING LOOK-AHEAD SEARCH 审中-公开

    公开(公告)号：US20240185070A1

    公开(公告)日：2024-06-06

    申请号：US18528640

    申请日：2023-12-04

    Applicant: DeepMind Technologies Limited

    Inventor： Karen Simonyan ,  David Silver ,  Julian Schrittwieser

    IPC: G06N3/08 ,  G06N7/01

    CPC classification number: G06N3/08 ,  G06N7/01

    Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network. One of the methods includes receiving an observation characterizing a current state of the environment; determining a target network output for the observation by performing a look ahead search of possible future states of the environment starting from the current state until the environment reaches a possible future state that satisfies one or more termination criteria, wherein the look ahead search is guided by the neural network in accordance with current values of the network parameters; selecting an action to be performed by the agent in response to the observation using the target network output generated by performing the look ahead search; and storing, in an exploration history data store, the target network output in association with the observation for use in updating the current values of the network parameters.

    Generating output examples using bit blocks
    7.
    发明授权
    Generating output examples using bit blocks 有权

    公开(公告)号：US11853861B2

    公开(公告)日：2023-12-26

    申请号：US17962881

    申请日：2022-10-10

    Applicant: DeepMind Technologies Limited

    Inventor： Nal Emmerich Kalchbrenner ,  Karen Simonyan ,  Erich Konrad Elsen

    IPC: G06N3/04 ,  G06N3/047 ,  G06N3/088 ,  G06N3/045

    CPC classification number: G06N3/047 ,  G06N3/045 ,  G06N3/088

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes receiving a request to generate an output example of a particular type, accessing dependency data, and generating the output example by, at each of a plurality of generation time steps: identifying one or more current blocks for the generation time step, wherein each current block is a block for which the values of the bits in all of the other blocks identified in the dependency for the block have already been generated; and generating the values of the bits in the current blocks for the generation time step conditioned on, for each current block, the already generated values of the bits in the other blocks identified in the dependency for the current block.

    TRAINING ACTION SELECTION NEURAL NETWORKS USING LOOK-AHEAD SEARCH
    8.
    发明申请
    TRAINING ACTION SELECTION NEURAL NETWORKS USING LOOK-AHEAD SEARCH 有权

    公开(公告)号：US20230084700A1

    公开(公告)日：2023-03-16

    申请号：US17948016

    申请日：2022-09-19

    Applicant: DeepMind Technologies Limited

    Inventor： Karen Simonyan ,  David Silver ,  Julian Schrittwieser

    IPC: G06N3/08 ,  G06N7/00

    Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network. One of the methods includes receiving an observation characterizing a current state of the environment; determining a target network output for the observation by performing a look ahead search of possible future states of the environment starting from the current state until the environment reaches a possible future state that satisfies one or more termination criteria, wherein the look ahead search is guided by the neural network in accordance with current values of the network parameters; selecting an action to be performed by the agent in response to the observation using the target network output generated by performing the look ahead search; and storing, in an exploration history data store, the target network output in association with the observation for use in updating the current values of the network parameters.

Patent Agency Ranking