Many control problems in the robotics field can be cast as partially observed Markovian decision problems (POMDPs), an optimal control formalism. Finding optimal solutions to such problems in general, however is known to be intractable. It has often been observed that in practice, simple structured controllers suffice for good sub-optimal control, and recent research in the artificial intelligence community has focused on policy search methods as techniques for finding sub-optimal controllers when such structured controllers do exist. Traditional model-based reinforcement learning algorithms make a certainty equivalence assumption on their learned models and calculate optimal policies for a maximum-likelihood Markovian model. We consider algorithms that evaluate and synthesize controllers under distributions of Markovian models. Previous work has demonstrated that algorithms that maximize mean reward with respect to model uncertainty leads to safer and more robust controllers. We consider briefly other performance criterion that emphasize robustness and exploration in the search for controllers, and note the relation with experiment design and active learning. To validate the power of the approach on a robotic application we demonstrate the presented learning control algorithm by flying an autonomous helicopter. We show that the controller learned is robust and delivers good performance in this real-world domain.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Autonomous helicopter control using reinforcement learning policy search methods


    Beteiligte:
    Bagnell, J.A. (Autor:in) / Schneider, J.G. (Autor:in)


    Erscheinungsdatum :

    2001


    Format / Umfang :

    6 Seiten, 12 Quellen




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch





    Autonomous Micro-helicopter Control Based on Reinforcement Learning with Replacing Eligibility Traces

    Yang, Y.-j. / Cheng, J.-s. / Chen, J.-p. et al. | British Library Online Contents | 2003


    Deep Reinforcement Learning for Autonomous Search and Rescue

    Zuluaga, Juan Gonzalo Carcamo / Leidig, Jonathan P. / Trefftz, Christian et al. | IEEE | 2018