A novel robot learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated. PSL is a model-free prediction algorithm inspired by the dynamic temporal difference algorithm S-Learning. While S-Learning has previously been applied as a reinforcement learning algorithm for robots, PSL is here applied to a Learning from Demonstration problem. The proposed algorithm is evaluated on four tasks using a Khepera II robot. PSL builds a model from demonstrated data which is used to repeat the demonstrated behavior. After training, PSL can control the robot by continually predicting the next action, based on the sequence of passed sensor and motor events. PSL was able to successfully learn and repeat the first three (elementary) tasks, but it was unable to successfully repeat the fourth (composed) behavior. The results indicate that PSL is suitable for learning problems up to a certain complexity, while higher level coordination is required for learning more complex behaviors.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Model-free learning from demonstration


    Beteiligte:

    Erscheinungsdatum :

    2010-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Model-free learning from demonstration

    Billing, Erik / Hellström, Thomas / Janlert, Lars Erik | BASE | 2010

    Freier Zugriff

    Learning from Demonstration

    Ertel, Wolfgang | TIB AV-Portal | 2010


    Predictive learning from demonstration

    Billing, Erik / Hellström, Thomas / Janlert, Lars Erik | BASE | 2011

    Freier Zugriff

    Predictive learning from demonstration

    Billing, Erik / Hellström, Thomas / Janlert, Lars Erik | BASE | 2011

    Freier Zugriff