In this thesis, we contribute to new directions within Reinforcement Learning, which are important for many practical applications such as the control of biomechanical models. We deepen the mathematical foundations of Reinforcement Learning by deriving theoretical results inspired by classical optimal control theory. In our derivations, Deep Reinforcement Learning serves as our starting point. Based on its working principle, we derive a new type of Reinforcement Learning framework by replacing the neural network by a suitable ordinary differential equation. Coming up with profound mathematical results within this differential equation based framework turns out to be a challenging research task, which we address in this thesis. Especially the derivation of optimality conditions takes a central role in our investigation. We establish new optimality conditions tailored to our specific situation and analyze a resulting gradient based approach. Finally, we illustrate the power, working principle and versatility of this approach by performing control tasks in the context of a navigation in the two dimensional plane, robot motions, and actuations of a human arm model.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Differential Equation Based Framework for Deep Reinforcement Learning


    Beteiligte:

    Erscheinungsdatum :

    2021-01-01


    Anmerkungen:

    Fraunhofer ITWM


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Framework for control and deep reinforcement learning in traffic

    Wu, Cathy / Parvate, Kanaad / Kheterpal, Nishant et al. | IEEE | 2017


    Deep Reinforcement Learning

    Huang, Xiaowei / Jin, Gaojie / Ruan, Wenjie | Springer Verlag | 2012



    DEEP REINFORCEMENT LEARNING FOR A GENERAL FRAMEWORK FOR MODEL-BASED LONGITUDINAL CONTROL

    PATHAK SHASHANK / BAG SUVAM / NADKARNI VIJAY JAYANT | Europäisches Patentamt | 2020

    Freier Zugriff

    DEEP REINFORCEMENT LEARNING FOR A GENERAL FRAMEWORK FOR MODEL-BASED LONGITUDINAL CONTROL

    PATHAK SHASHANK / BAG SUVAM / NADKARNI VIJAY JAYANT | Europäisches Patentamt | 2020

    Freier Zugriff