中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.014 seconds)

    REINFORCEMENT LEARNING ALGORITHM SEARCH
    1.
    发明申请
    REINFORCEMENT LEARNING ALGORITHM SEARCH 有权

    公开(公告)号：US20220391687A1

    公开(公告)日：2022-12-08

    申请号：US17338093

    申请日：2021-06-03

    Applicant: Google LLC

    Inventor： John Dalton Co-Reyes ,  Yingjie Miao ,  Daiyi Peng ,  Sergey Vladimir Levine ,  Quoc V. Le ,  Honglak Lee ,  Aleksandra Faust

    IPC: G06N3/08 ,  G06F11/34 ,  G06F16/901

    Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating and searching reinforcement learning algorithms. In some implementations, a computer-implemented system generates a sequence of candidate reinforcement learning algorithms. Each candidate reinforcement learning algorithm in the sequence is configured to receive an input environment state characterizing a state of an environment and to generate an output that specifies an action to be performed by an agent interacting with the environment. For each candidate reinforcement learning algorithm in the sequence, the system performs a performance evaluation for a set of a plurality of training environments. For each training environment, the system adjusts a set of environment-specific parameters of the candidate reinforcement learning algorithm by performing training of the candidate reinforcement learning algorithm to control a corresponding agent in the training environment. The system generates an environment-specific performance metric for the candidate reinforcement learning algorithm that measures a performance of the candidate reinforcement learning algorithm in controlling the corresponding agent in the training environment as a result of the training. After performing training in the set of training environments, the system generates a summary performance metric for the candidate reinforcement learning algorithm by combining the environment-specific performance metrics generated for the set of training environments. After evaluating each of the candidate reinforcement learning algorithms in the sequence, the system selects one or more output reinforcement learning algorithms from the sequence based on the summary performance metrics of the candidate reinforcement learning algorithms.

    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS
    2.
    发明申请
    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS 有权

    公开(公告)号：US20210334320A1

    公开(公告)日：2021-10-28

    申请号：US17280027

    申请日：2019-09-27

    Applicant: Google LLC

    Inventor： Aleksandra Faust ,  Dilek Hakkani-Tur ,  Izzeddin Gur ,  Ulrich Rueckert

    IPC: G06F16/954 ,  G06N3/04 ,  G06F16/953

    Abstract: The present disclosure is generally directed to methods, apparatus, and computer-readable media (transitory and non-transitory) for learning to automatically navigate interactive web documents and/or websites. More particularly, various approaches are presented for training various deep Q network (DQN) agents to perform various tasks associated with reinforcement learning, including hierarchical reinforcement learning, in challenging web navigation environments with sparse rewards and large state and action spaces. These agents include a web navigation agent that can use learned value function(s) to automatically navigate through interactive web documents, as well as a training agent, referred to herein as a “meta-trainer,” that can be trained to generate synthetic training examples. Some approaches described herein may be implemented when expert demonstrations are available. Other approaches described herein may be implemented when expert demonstrations are not available. In either case, dense, potential-based rewards may be used to augment the training.

    Systems and Methods for Training a Machine Learned Model for Agent Navigation
    3.
    发明申请
    Systems and Methods for Training a Machine Learned Model for Agent Navigation 有权

    公开(公告)号：US20210182620A1

    公开(公告)日：2021-06-17

    申请号：US16717471

    申请日：2019-12-17

    Applicant: Google LLC

    Inventor： Jie Tan ,  Sehoon Ha ,  Tingnan Zhang ,  Xinlei Pan ,  Brian Andrew Ichter ,  Aleksandra Faust

    IPC: G06K9/62 ,  G05D1/00 ,  G06N3/08 ,  G06N3/04

    Abstract: A computer-implemented method is disclosed for training one or more machine-learned models. The method can include inputting a first image frame and a second image frame into a feature disentanglement model and receiving, as an output of the machine-learned feature disentanglement model, a state feature and a perspective feature. The method can include inputting the state feature and the perspective feature into a machine-learned decoder model and receiving, as an output of the machine-learned decoder model, the reconstructed image frame. The method can include comparing the reconstructed image frame with a third image frame corresponding with the location and the perspective orientation. The method can include adjusting one or more parameters of the machine-learned feature disentanglement model based on the comparison of the reconstructed image frame and the third image frame.

    Automatic navigation of interactive web documents
    6.
    发明授权
    Automatic navigation of interactive web documents 有权

    公开(公告)号：US12118052B2

    公开(公告)日：2024-10-15

    申请号：US18234766

    申请日：2023-08-16

    Applicant: GOOGLE LLC

    Inventor： Aleksandra Faust ,  Dilek Hakkani-Tur ,  Izzeddin Gur ,  Ulrich Rueckert

    IPC: G06F16/954 ,  G06F16/953 ,  G06N3/04

    CPC classification number: G06F16/954 ,  G06F16/953 ,  G06N3/04

    Abstract: The present disclosure is generally directed to methods, apparatus, and computer-readable media (transitory and non-transitory) for learning to automatically navigate interactive web documents and/or websites. More particularly, various approaches are presented for training various deep Q network (DQN) agents to perform various tasks associated with reinforcement learning, including hierarchical reinforcement learning, in challenging web navigation environments with sparse rewards and large state and action spaces. These agents include a web navigation agent that can use learned value function(s) to automatically navigate through interactive web documents, as well as a training agent, referred to herein as a “meta-trainer,” that can be trained to generate synthetic training examples. Some approaches described herein may be implemented when expert demonstrations are available. Other approaches described herein may be implemented when expert demonstrations are not available. In either case, dense, potential-based rewards may be used to augment the training.

    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS
    8.
    发明公开
    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS 审中-公开

    公开(公告)号：US20230394102A1

    公开(公告)日：2023-12-07

    申请号：US18234766

    申请日：2023-08-16

    Applicant: GOOGLE LLC

    Inventor： Aleksandra Faust ,  Dilek Hakkani-Tur ,  Izzeddin Gur ,  Ulrich Rueckert

    IPC: G06F16/954 ,  G06F16/953 ,  G06N3/04

    CPC classification number: G06F16/954 ,  G06F16/953 ,  G06N3/04

    Abstract: The present disclosure is generally directed to methods, apparatus, and computer-readable media (transitory and non-transitory) for learning to automatically navigate interactive web documents and/or websites. More particularly, various approaches are presented for training various deep Q network (DQN) agents to perform various tasks associated with reinforcement learning, including hierarchical reinforcement learning, in challenging web navigation environments with sparse rewards and large state and action spaces. These agents include a web navigation agent that can use learned value function(s) to automatically navigate through interactive web documents, as well as a training agent, referred to herein as a “meta-trainer,” that can be trained to generate synthetic training examples. Some approaches described herein may be implemented when expert demonstrations are available. Other approaches described herein may be implemented when expert demonstrations are not available. In either case, dense, potential-based rewards may be used to augment the training.

    CONTROLLING A ROBOT BASED ON FREE-FORM NATURAL LANGUAGE INPUT
    9.
    发明申请
    CONTROLLING A ROBOT BASED ON FREE-FORM NATURAL LANGUAGE INPUT 有权

    公开(公告)号：US20210086353A1

    公开(公告)日：2021-03-25

    申请号：US17040299

    申请日：2019-03-22

    Applicant: Google LLC

    Inventor： Pararth Shah ,  Dilek Hakkani-Tur ,  Juliana Kew ,  Marek Fiser ,  Aleksandra Faust

    IPC: B25J9/16 ,  G10L25/78 ,  G10L15/22 ,  G10L15/18 ,  G06K9/00 ,  G06K9/62 ,  G10L15/16 ,  G06T7/593 ,  G06K9/72 ,  B25J13/08 ,  G05D1/02 ,  G05B13/02 ,  G06N3/04

    Abstract: Implementations relate to using deep reinforcement learning to train a model that can be utilized, at each of a plurality of time steps, to determine a corresponding robotic action for completing a robotic task. Implementations additionally or alternatively relate to utilization of such a model in controlling a robot. The robotic action determined at a given time step utilizing such a model can be based on: current sensor data associated with the robot for the given time step, and free-form natural language input provided by a user. The free-form natural language input can direct the robot to accomplish a particular task, optionally with reference to one or more intermediary steps for accomplishing the particular task. For example, the free-form natural language input can direct the robot to navigate to a particular landmark, with reference to one or more intermediary landmarks to be encountered in navigating to the particular landmark.

    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS
    10.
    发明申请
    AUTOMATIC NAVIGATION OF INTERACTIVE WEB DOCUMENTS 有权

    公开(公告)号：US20250077603A1

    公开(公告)日：2025-03-06

    申请号：US18952242

    申请日：2024-11-19

    Applicant: GOOGLE LLC

    Inventor： Aleksandra Faust ,  Dilek Hakkani-Tur ,  Izzeddin Gur ,  Ulrich Rueckert

    IPC: G06F16/954 ,  G06F16/953 ,  G06N3/04

    Abstract: The present disclosure is generally directed to methods, apparatus, and computer-readable media (transitory and non-transitory) for learning to automatically navigate interactive web documents and/or websites. More particularly, various approaches are presented for training various deep Q network (DQN) agents to perform various tasks associated with reinforcement learning, including hierarchical reinforcement learning, in challenging web navigation environments with sparse rewards and large state and action spaces. These agents include a web navigation agent that can use learned value function(s) to automatically navigate through interactive web documents, as well as a training agent, referred to herein as a “meta-trainer,” that can be trained to generate synthetic training examples. Some approaches described herein may be implemented when expert demonstrations are available. Other approaches described herein may be implemented when expert demonstrations are not available. In either case, dense, potential-based rewards may be used to augment the training.

Patent Agency Ranking