中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

43 records (took 0.021 seconds)

    Reinforcement learning for active sequence processing
    22.
    发明授权
    Reinforcement learning for active sequence processing 有权

    公开(公告)号：US12175737B2

    公开(公告)日：2024-12-24

    申请号：US17773789

    申请日：2020-11-13

    Applicant: DEEPMIND TECHNOLOGIES LIMITED

    Inventor： Viorica Patraucean ,  Bilal Piot ,  Joao Carreira ,  Volodymyr Mnih ,  Simon Osindero

    IPC: G06V10/82 ,  G06N3/045 ,  G06N3/048

    Abstract: A system that is configured to receive a sequence of task inputs and to perform a machine learning task is described. The system includes a reinforcement learning (RL) neural network and a task neural network. The RL neural network is configured to: generate, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, and provide the respective decision of each task input to the task neural network. The task neural network is configured to: receive the sequence of task inputs, receive, from the RL neural network, for each task input of the sequence of task inputs, a respective decision that determines whether to encode the task input or to skip the task input, process each of the un-skipped task inputs in the sequence of task inputs to generate a respective accumulated feature for the un-skipped task input, wherein the respective accumulated feature characterizes features of the un-skipped task input and of previous un-skipped task inputs in the sequence, and generate a machine learning task output for the machine learning task based on the last accumulated feature generated for the last un-skipped task input in the sequence.

    Controlling agents using amortized Q learning
    25.
    发明授权
    Controlling agents using amortized Q learning 有权

    公开(公告)号：US11868866B2

    公开(公告)日：2024-01-09

    申请号：US17287306

    申请日：2019-11-18

    Applicant: DeepMind Technologies Limited

    Inventor： Tom Van de Wiele ,  Volodymyr Mnih ,  Andriy Mnih ,  David Constantine Patrick Warde-Farley

    IPC: G06N3/04 ,  G06N3/047 ,  G06N3/006 ,  G06N3/084

    CPC classification number: G06N3/047 ,  G06N3/006 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment. One of the methods includes receiving a current observation; processing the current observation using a proposal neural network to generate a proposal output that defines a proposal probability distribution over a set of possible actions that can be performed by the agent to interact with the environment; sampling (i) one or more actions from the set of possible actions in accordance with the proposal probability distribution and (ii) one or more actions randomly from the set of possible actions; processing the current observation and each sampled action using a Q neural network to generate a Q value; and selecting an action using the Q values generated by the Q neural network.

    Image processing with recurrent attention
    28.
    发明授权
    Image processing with recurrent attention 有权

    公开(公告)号：US11354548B1

    公开(公告)日：2022-06-07

    申请号：US16927159

    申请日：2020-07-13

    Applicant: DeepMind Technologies Limited

    Inventor： Volodymyr Mnih ,  Koray Kavukcuoglu

    IPC: G06K9/62 ,  G06V10/44 ,  G06V20/80 ,  G06V30/194 ,  G06V30/413

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.

    UNSUPERVISED CONTROL USING LEARNED REWARDS
    30.
    发明申请
    UNSUPERVISED CONTROL USING LEARNED REWARDS 审中-公开

    公开(公告)号：US20190354869A1

    公开(公告)日：2019-11-21

    申请号：US16416920

    申请日：2019-05-20

    Applicant: DeepMind Technologies Limited

    Inventor： David Constantine Patrick Warde-Farley ,  Volodymyr Mnih

    IPC: G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent that interacts with an environment. In one aspect, a system comprises: an action selection subsystem that selects actions to be performed by the agent using an action selection policy generated using an action selection neural network; a reward subsystem that is configured to: receive an observation characterizing a current state of the environment and an observation characterizing a goal state of the environment; generate a reward using an embedded representation of the observation characterizing the current state of the environment and an embedded representation of the observation characterizing the goal state of the environment; and a training subsystem that is configured to train the action selection neural network based on the rewards generated by the reward subsystem using reinforcement learning techniques.

Patent Agency Ranking