Policy rollout is a method for the online computation of future costs in approximate dynamic programming and has been utilized for various problems, including sensor management. In previous work, it has predominately been applied to the selection of actions from discrete sets. In this article, we present methods for action selection from continuous sets and analyze their tradeoffs. The methods are evaluated on the problem of sensor path planning, with the intent of minimizing the time to localize an emitter using bearing measurements.


    Access

    Download


    Export, share and cite



    Title :

    Policy Rollout Action Selection in Continuous Domains for Sensor Path Planning


    Contributors:


    Publication date :

    2021-08-01


    Size :

    2719245 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Cooperative Mission Planning Using Rollout Policy Optimization

    Hajkarim, Sina M. H. / Menon, Prathyush P. / Ghose, Debasish | AIAA | 2024


    'Enterprise' rollout

    Tema Archive | 1976


    Rollout-Based Interactive Motion Planning for Automated Vehicles *

    Wang, Ning / Chen, Xiao / Martensson, Jonas | IEEE | 2023


    OH-X rollout

    Online Contents | 1996


    DYNAMIC ROLLOUT PREVENTION HOOK

    MANESS SAMUEL GENE | European Patent Office | 2019

    Free access