In this chapter, the authors modify the reinforcement learning (RL) methods to overcome the overestimation and the dimension problems for the robust control problem under the worst‐case uncertainty. The objective of robust control is to achieve robust performance in presence of disturbances. Most robust controllers using RL are based on the actor‐critic algorithms and Q‐learning. The authors prove that the reinforcement learning with the k‐nearest neighbors (kNN) and double Q‐learning modifications guarantees the robust controller under worst‐case uncertainty convergence with a near‐optimal value. Optimization procedures can be used for the kNN rule to find the optimal number of k‐nearest neighbors. The authors discuss two cases: ideal control without uncertainty and robust control with worst‐case uncertainty. They compare continuous‐time critic learning with the H 2 solution, and the continuous‐time actor‐critic learning method. The results of the simulation and the experiment show that the RL algorithms are robust with sub‐optimal control policy with respect to the worst‐case uncertainty.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Robot Control in Worst‐Case Uncertainty Using Reinforcement Learning


    Beteiligte:
    Yu, Wen (Autor:in) / Perrusquía, Adolfo (Autor:in)


    Erscheinungsdatum :

    05.10.2021


    Format / Umfang :

    34 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Flight Control Law Clearance Using Worst-Case Inputs Under Parameter Uncertainty

    Diepolder, Johannes / Ben-Asher, Joseph Z. / Holzapfel, Florian | AIAA | 2020

    Freier Zugriff


    Modeling and Computing Worst-Case Uncertainty Combinations for Flight Control Systems Analysis

    Thomas Mannchen / Declan G. Bates / Ian Postlethwaite | AIAA | 2002


    Human-robot interaction control using reinforcement learning

    Yu, Wen / Perrusquia, Adolfo | TIBKAT | 2022


    Linear-Quadratic Worst Case Control

    Juge, M. K. / Bryson, A. E. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 1996