中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

615 records (took 0.028 seconds)

    Neural programming
    5.
    发明授权
    Neural programming 有权

    公开(公告)号：US12260334B2

    公开(公告)日：2025-03-25

    申请号：US18497924

    申请日：2023-10-30

    Applicant: DeepMind Technologies Limited

    Inventor： Scott Ellison Reed ,  Joao Ferdinando Gomes de Freitas

    IPC: G06N3/044 ,  G06N3/08 ,  G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural programming. One of the methods includes processing a current neural network input using a core recurrent neural network to generate a neural network output; determining, from the neural network output, whether or not to end a currently invoked program and to return to a calling program from the set of programs; determining, from the neural network output, a next program to be called; determining, from the neural network output, contents of arguments to the next program to be called; receiving a representation of a current state of the environment; and generating a next neural network input from an embedding for the next program to be called and the representation of the current state of the environment.

    Fast exploration and learning of latent graph models
    6.
    发明授权
    Fast exploration and learning of latent graph models 有权

    公开(公告)号：US12189688B2

    公开(公告)日：2025-01-07

    申请号：US18373870

    申请日：2023-09-27

    Applicant: DeepMind Technologies Limited

    Inventor： Sivaramakrishnan Swaminathan ,  Meet Kirankumar Dave ,  Miguel Lazaro-Gredilla ,  Dileep George

    IPC: G06F16/901 ,  G06F17/12

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a graph model representing an environment being interacted with by an agent. In one aspect, one of the methods include: obtaining experience data; using the experience data to update a visitation count for each of one or more state-action pairs represented by the graph model; and at each of multiple environment exploration steps: computing a utility measure for each of the one or more state-action pairs represented by the graph model; determining, based on the utility measures, a sequence of one or more planned actions that have an information gain that satisfies a threshold; and controlling the agent to perform the sequence of one or more planned actions to cause the environment to transition from a state characterized by a last observation received after a last action in the experience data into a different state.

    PROGRAMMABLE REINFORCEMENT LEARNING SYSTEMS
    8.
    发明申请
    PROGRAMMABLE REINFORCEMENT LEARNING SYSTEMS 有权

    公开(公告)号：US20240394504A1

    公开(公告)日：2024-11-28

    申请号：US18637279

    申请日：2024-04-16

    Applicant: DeepMind Technologies Limited

    Inventor： Misha Man Ray Denil ,  Sergio Gomez Colmenarejo ,  Serkan Cabi ,  David William Saxton ,  Joao Ferdinando Gomes de Freitas

    IPC: G06N3/006 ,  G06F18/21 ,  G06F18/2451 ,  G06N3/045 ,  G06N3/047 ,  G06N3/084

    Abstract: A reinforcement learning system is proposed comprising a plurality of property detector neural networks. Each property detector neural network is arranged to receive data representing an object within an environment, and to generate property data associated with a property of the object. A processor is arranged to receive an instruction indicating a task associated with an object having an associated property, and process the output of the plurality of property detector neural networks based upon the instruction to generate a relevance data item. The relevance data item indicates objects within the environment associated with the task. The processor also generates a plurality of weights based upon the relevance data item, and, based on the weights, generates modified data representing the plurality of objects within the environment. A neural network is arranged to receive the modified data and to output an action associated with the task.

    Training action selection neural networks using look-ahead search
    10.
    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.

Patent Agency Ranking