In this chapter, we show how to use reinforcement learning (RL) to generate a control policy for the same uncertain dynamical system considered in the previous chapters. Specifically, we present an online model-based RL (MBRL) algorithm that balances the often competing objectives of learning and safety by simultaneously learning the value function of an optimal control problem and the uncertain parameters of a dynamical system using real-time data. Central to our approach is a safe exploration framework based on the adaptive control barrier functions introduced in Chap. 5. We start by formulating an infinite-horizon optimal control problem as an RL problem in Sect. 8.1. Approximations for the value function used in the RL algorithm are discussed in Sect. 8.2. The main part of this chapter is Sect. 8.3, where we present the online MBRL algorithm. We illustrate the method with numerical examples in Sect. 8.4 and conclude with final remarks, references, and suggestions for further reading in Sect. 8.5.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Safe Exploration in Model-Based Reinforcement Learning


    Weitere Titelangaben:

    synth. Lectures on Computer sci.


    Beteiligte:
    Cohen, Max (Autor:in) / Belta, Calin (Autor:in)


    Erscheinungsdatum :

    2023-05-16


    Format / Umfang :

    31 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    SHERPA: a safe exploration algorithm for Reinforcement Learning controllers

    Mannucci, Tommaso / Van Kampen, Erik-Jan / de Visser, Coen C. et al. | AIAA | 2015


    Human Demonstrations for Fast and Safe Exploration in Reinforcement Learning

    Schonebaum, Gerben / Junell, Jaime / Van Kampen, Erik-Jan | AIAA | 2017


    Safe robot execution in model-based reinforcement learning

    Martínez Martínez, David / Alenyà Ribas, Guillem / Torras, Carme | BASE | 2015

    Freier Zugriff

    Safe robot execution in model-based reinforcement learning

    Martínez, David / Alenyà, Guillem / Torras, Carme | BASE | 2015

    Freier Zugriff

    Temporal Logic Guided Safe Model-Based Reinforcement Learning

    Cohen, Max / Belta, Calin | Springer Verlag | 2023