META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY

    公开(公告)号:US20240046091A1

    公开(公告)日:2024-02-08

    申请号:US18484793

    申请日:2023-10-11

    CPC classification number: G06N3/08 G06N20/00

    Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

    META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY

    公开(公告)号:US20220058482A1

    公开(公告)日:2022-02-24

    申请号:US17391427

    申请日:2021-08-02

    Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

    META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY

    公开(公告)号:US20240037400A1

    公开(公告)日:2024-02-01

    申请号:US18484805

    申请日:2023-10-11

    CPC classification number: G06N3/08 G06N20/00

    Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

    META IMITATION LEARNING WITH STRUCTURED SKILL DISCOVERY

    公开(公告)号:US20240046092A1

    公开(公告)日:2024-02-08

    申请号:US18484816

    申请日:2023-10-11

    CPC classification number: G06N3/08 G06N20/00

    Abstract: A method for acquiring skills through imitation learning by employing a meta imitation learning framework with structured skill discovery (MILD) is presented. The method includes learning behaviors or tasks, by an agent, from demonstrations: by learning to decompose the demonstrations into segments, via a segmentation component, the segments corresponding to skills that are transferrable across different tasks, learning relationships between the skills that are transferrable across the different tasks, employing, via a graph generator, a graph neural network for learning implicit structures of the skills from the demonstrations to define structured skills, and generating policies from the structured skills to allow the agent to acquire the structured skills for application to one or more target tasks.

Patent Agency Ranking