A method and system for controlling a device includes training a low-level policy to form a trained low-level policy and a low-level value function to form a trained goal conditioned value function, wherein training is performed using a static data set using goal conditioned episodes, training a high-level goal planner having high level goals having high-level sub-goals corresponding to a plurality of future time steps using the low-level value function to maximize a cumulative reward over the sub-goals for the plurality of future time steps so that the sub-goals are reachable by the low-level policy, obtaining an observation of a device, and generating an executable action using the low-level policy and the high-level goal planner and operating the device with the executable action.


    Access

    Download


    Export, share and cite



    Title :

    Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning


    Contributors:
    HUANG MINGLEI (author) / ZHAN WEI (author) / TOMIZUKA MASAYOSHI (author) / TANG CHEN (author) / LI JINNING (author)

    Publication date :

    2024-10-10


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06V



    GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generation

    Ransiek, Joshua / Plaum, Johannes / Langner, Jacob et al. | IEEE | 2024



    From Prediction to Planning With Goal Conditioned Lane Graph Traversals

    Hallgarten, Marcel / Stoll, Martin / Zell, Andreas | IEEE | 2023


    Data-driven offline reinforcement learning approach for quadrotor’s motion and path planning

    ZHAO, Haoran / FU, Hang / YANG, Fan et al. | Elsevier | 2024

    Free access