In robotics, lower-level controllers are typically used to make the robot solve a specific task in a fixed context. For example, the lower-level controller can encode a hitting movement while the context defines the target coordinates to hit. However, in many learning problems the context may change between task executions. To adapt the policy to a new context, we utilize a hierarchical approach by learning an upper-level policy that generalizes the lower-level controllers to new contexts. A common approach to learn such upper-level policies is to use policy search. However, the majority of current contextual policy search approaches are model-free and require a high number of interactions with the robot and its environment. Model-based approaches are known to significantly reduce the amount of robot experiments, however, current model-based techniques cannot be applied straightforwardly to the problem of learning contextual upper-level policies. They rely on specific parametrizations of the policy and the reward function, which are often unrealistic in the contextual policy search formulation. In this paper, we propose a novel model-based contextual policy search algorithm that is able to generalize lower-level controllers, and is data-efficient. Our approach is based on learned probabilistic forward models and information theoretic policy search. Unlike current algorithms, our method does not require any assumption on the parametrization of the policy or the reward function. We show on complex simulated robotic tasks and in a real robot experiment that the proposed learning framework speeds up the learning process by up to two orders of magnitude in comparison to existing methods, while learning high quality policies.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Model-based contextual policy search for data-efficient generalization of robot skills


    Beteiligte:
    Kupcsik, A (Autor:in) / Deisenroth, MP (Autor:in) / Peters, J (Autor:in) / Poh, LA (Autor:in) / Vadakkepat, P (Autor:in) / Neumann, G (Autor:in)

    Erscheinungsdatum :

    2017-06-01


    Anmerkungen:

    Artificial Intelligence , 247 pp. 415-439. (2017)


    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Contextual policy search for micro-data robot motion learning through covariate Gaussian process latent variable models

    Delgado-Guerrero, Juan Antonio / Colomé, Adrià / Torras, Carme | BASE | 2020

    Freier Zugriff

    Gradient-Aware Model-Based Policy Search

    Pierluca D'Oro / Alberto Maria Metelli / Andrea Tirinzoni et al. | BASE | 2020

    Freier Zugriff

    Skills-Oriented Robot Programming

    Archibald, C. / Petriu, E. | British Library Conference Proceedings | 1993



    Guided policy search for a lightweight industrial robot arm

    White, Jack | BASE | 2018

    Freier Zugriff