中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.015 seconds)

    SYSTEM AND METHOD FOR IMITATION LEARNING
    1.
    发明公开
    SYSTEM AND METHOD FOR IMITATION LEARNING 审中-公开

    公开(公告)号：US20230325712A1

    公开(公告)日：2023-10-12

    申请号：US18109975

    申请日：2023-02-15

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Jin Chul CHOI

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: The present disclosure relates to a system and method for imitation learning. The system for imitation learning may include a data augmentation device configured to acquire a plurality of augmented data sets from a plurality of demonstration data sets corresponding to an expert's demonstration behavior trajectory using a behavioral replication model that infers behavioral data from input state data and an inverse behavioral replication model that infers state data from input behavioral data, and an imitation learning device configured to perform imitation learning to derive a model that outputs behavioral data similar to an expert in a specific state using the plurality of demonstration data sets and the plurality of augmented data sets, in which the plurality of demonstration data sets and the plurality of augmented data sets each include a pair of corresponding state data and behavioral data.

    ELECTRONIC DEVICE PERFORMING IMITATION LEARNING FOR BEHAVIOR AND OPERATION METHOD THEREOF
    2.
    发明申请
    ELECTRONIC DEVICE PERFORMING IMITATION LEARNING FOR BEHAVIOR AND OPERATION METHOD THEREOF 有权

    公开(公告)号：US20220343118A1

    公开(公告)日：2022-10-27

    申请号：US17551929

    申请日：2021-12-15

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Jin Chul CHOI

    IPC: G06K9/62

    Abstract: Disclosed is a method of operating an electronic device for learning a behavior of a user, which includes receiving input data related to the behavior of the user, obtaining first behavior trajectory information by processing the input data, generating an initial behavior policy based on the first behavior trajectory information, obtaining second behavior trajectory information based on the initial behavior policy, sampling the first behavior trajectory information and the second behavior trajectory information, training an evaluation model for classifying the first behavior trajectory information and the second behavior trajectory information, and updating the initial behavior policy based on the evaluation model.

    METHOD AND APPARATUS FOR MANAGING RESOURCE
    4.
    发明申请
    METHOD AND APPARATUS FOR MANAGING RESOURCE 有权
    管理资源的方法和装置

    公开(公告)号：US20150007192A1

    公开(公告)日：2015-01-01

    申请号：US14314225

    申请日：2014-06-25

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Hyung Kyu LEE ,  Soon Hyun KWON ,  Dong-Hwan PARK ,  Kwang Soo KIM ,  Yoon Sik Yoo ,  Jin Chul CHOI ,  Sunjin KIM ,  Hyochan BANG

    IPC: G06F9/50

    CPC classification number: H04L67/12 ,  G06F9/52 ,  H04W4/70

    Abstract: According to an exemplary embodiment of the present invention, a method for managing a resource using an apparatus for managing a resource is provided. The apparatus for managing a resource generates a first instance for a first community using a first ontology class about communities including at least one resource as a member according to a goal. The apparatus for managing a resource generates a second instance for a first resource using a second ontology class about resources. Further, the apparatus for managing a resource estimates a relation between the first instance and the second instance.

    Abstract translation: 根据本发明的示例性实施例，提供了一种使用用于管理资源的装置来管理资源的方法。 用于管理资源的装置根据目标使用关于包括至少一个资源的社区的第一本体类为第一社区生成第一实例作为成员。 用于管理资源的装置使用关于资源的第二本体类为第一资源生成第二实例。 此外，用于管理资源的装置估计第一实例与第二实例之间的关系。

    DIGITAL TWIN FEDERATION SYSTEM FOR INTEROPERABILITY AND FEDERATION BETWEEN DIGITAL TWINS AND OPERATING METHOD THEREOF
    5.
    发明申请
    DIGITAL TWIN FEDERATION SYSTEM FOR INTEROPERABILITY AND FEDERATION BETWEEN DIGITAL TWINS AND OPERATING METHOD THEREOF 有权

    公开(公告)号：US20250117555A1

    公开(公告)日：2025-04-10

    申请号：US18906300

    申请日：2024-10-04

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Il Soon JANG ,  Dae Ho KIM ,  Chan Won PARK ,  Soon Yong SONG ,  Jin Chul CHOI

    IPC: G06F30/27 ,  G06F111/02

    Abstract: A digital twin federation system for interoperability and federation between digital twins and an operating method thereof are provided. The digital twin federation system includes single digital twins to be federated, a metadata repository that stores metadata on the single digital twins and a federated digital twin, a federated digital twin generated by federating the single digital twins, and a management device that searches for a single digital twin providing a specific service among the single digital twins from the metadata repository through a search function to determine the single digital twin to be a digital twin for the federated digital twin, generates the federated digital twin where the single digital twins are federated, and generates a tool for providing a service of the federated digital twin, thereby expanding existing services and provide new services by federating digital twins, and easily solving problems involving domains through simulation and visualization.

    METHOD AND APPARATUS FOR REINFORCEMENT MACHINE LEARNING
    6.
    发明申请
    METHOD AND APPARATUS FOR REINFORCEMENT MACHINE LEARNING 有权

    公开(公告)号：US20210019644A1

    公开(公告)日：2021-01-21

    申请号：US16929975

    申请日：2020-07-15

    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

    Inventor： Hyunseok KIM ,  Myung Eun KIM ,  Seonghyun KIM ,  Young Sung SON ,  Jongkwon SON ,  Soonyong SONG ,  Donghun LEE ,  Ingook JANG ,  Jin Chul CHOI

    IPC: G06N7/00 ,  G06N20/00

    Abstract: A method and an apparatus for exclusive reinforcement learning are provided, comprising: collecting information of states of an environment through the communication interface and performing a statistical analysis on the states using the collected information; determining a first state value of a first state among the states in a training phase and a second state value of a second state among the states in an inference phase based on analysis results of the statistical analysis; performing reinforcement learning by using one reinforcement learning unit of a plurality of reinforcement learning unit which performs reinforcement learnings from different perspectives according to the first state value; and selecting one of actions determined by the plurality of reinforcement learning unit based on the second state value and applying selected action to the environment.

Patent Agency Ranking