中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

34 records (took 0.022 seconds)

    DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS
    21.
    发明申请
    DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS 审中-公开

    公开(公告)号：US20200285909A1

    公开(公告)日：2020-09-10

    申请号：US16882373

    申请日：2020-05-22

    Applicant: DeepMind Technologies Limited

    Inventor： Martin Riedmiller ,  Roland Hafner ,  Mel Vecerik ,  Timothy Paul Lillicrap ,  Thomas Lampe ,  Ivaylo Popov ,  Gabriel Barth-Maron ,  Nicolas Manfred Otto Heess

    IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

    Data-efficient reinforcement learning for continuous control tasks
    22.
    发明授权
    Data-efficient reinforcement learning for continuous control tasks 有权

    公开(公告)号：US10664725B2

    公开(公告)日：2020-05-26

    申请号：US16528260

    申请日：2019-07-31

    Applicant: DeepMind Technologies Limited

    Inventor： Martin Riedmiller ,  Roland Hafner ,  Mel Vecerik ,  Timothy Paul Lillicrap ,  Thomas Lampe ,  Ivaylo Popov ,  Gabriel Barth-Maron ,  Nicolas Manfred Otto Heess

    IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

    SCALABLE AND COMPRESSIVE NEURAL NETWORK DATA STORAGE SYSTEM
    23.
    发明申请
    SCALABLE AND COMPRESSIVE NEURAL NETWORK DATA STORAGE SYSTEM 有权

    公开(公告)号：US20250053780A1

    公开(公告)日：2025-02-13

    申请号：US18662972

    申请日：2024-05-13

    Applicant: DeepMind Technologies Limited

    Inventor： Jack William Rae ,  Timothy Paul Lillicrap ,  Sergey Bartunov

    IPC: G06N3/045 ,  G06F16/22 ,  G06N3/08

    Abstract: A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

    Learned computer control using pointing device and keyboard actions
    24.
    发明授权
    Learned computer control using pointing device and keyboard actions 有权

    公开(公告)号：US12189870B2

    公开(公告)日：2025-01-07

    申请号：US18103309

    申请日：2023-01-30

    Applicant: DeepMind Technologies Limited

    Inventor： Peter Conway Humphreys ,  Timothy Paul Lillicrap ,  Tobias Markus Pohlen ,  Adam Anthony Santoro

    IPC: G06F3/023 ,  G06F3/033 ,  G06F40/284

    Abstract: A computer-implemented method for controlling a particular computer to execute a task is described. The method includes receiving a control input comprising a visual input, the visual input including one or more screen frames of a computer display that represent at least a current state of the particular computer; processing the control input using a neural network to generate one or more control outputs that are used to control the particular computer to execute the task, in which the one or more control outputs include an action type output that specifies at least one of a pointing device action or a keyboard action to be performed to control the particular computer; determining one or more actions from the one or more control outputs; and executing the one or more actions to control the particular computer.

    LEARNED COMPUTER CONTROL USING POINTING DEVICE AND KEYBOARD ACTIONS
    27.
    发明公开
    LEARNED COMPUTER CONTROL USING POINTING DEVICE AND KEYBOARD ACTIONS 审中-公开

    公开(公告)号：US20230244325A1

    公开(公告)日：2023-08-03

    申请号：US18103309

    申请日：2023-01-30

    Applicant: DeepMind Technologies Limited

    Inventor： Peter Conway Humphreys ,  Timothy Paul Lillicrap ,  Tobias Markus Pohlen ,  Adam Anthony Santoro

    IPC: G06F3/033 ,  G06F3/023 ,  G06F40/284

    CPC classification number: G06F3/033 ,  G06F3/023 ,  G06F40/284

    Abstract: A computer-implemented method for controlling a particular computer to execute a task is described. The method includes receiving a control input comprising a visual input, the visual input including one or more screen frames of a computer display that represent at least a current state of the particular computer; processing the control input using a neural network to generate one or more control outputs that are used to control the particular computer to execute the task, in which the one or more control outputs include an action type output that specifies at least one of a pointing device action or a keyboard action to be performed to control the particular computer; determining one or more actions from the one or more control outputs; and executing the one or more actions to control the particular computer.

    Selecting reinforcement learning actions using a low-level controller
    29.
    发明授权
    Selecting reinforcement learning actions using a low-level controller 有权

    公开(公告)号：US11210585B1

    公开(公告)日：2021-12-28

    申请号：US15594228

    申请日：2017-05-12

    Applicant: DeepMind Technologies Limited

    Inventor： Nicolas Manfred Otto Heess ,  Timothy Paul Lillicrap ,  Gregory Duncan Wayne ,  Yuval Tassa

    IPC: G06N3/08 ,  G06N3/00

    Abstract: Methods, systems, and apparatus for selecting actions to be performed by an agent interacting with an environment. One system includes a high-level controller neural network, low-level controller network, and subsystem. The high-level controller neural network receives an input observation and processes the input observation to generate a high-level output defining a control signal for the low-level controller. The low-level controller neural network receives a designated component of an input observation and processes the designated component and an input control signal to generate a low-level output that defines an action to be performed by the agent in response to the input observation. The subsystem receives a current observation characterizing a current state of the environment, determines whether criteria are satisfied for generating a new control signal, and based on the determination, provides appropriate inputs to the high-level and low-level controllers for selecting an action to be performed by the agent.

Patent Agency Ranking