IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), 1999, Barcelona (España) ; The categorization process defines sensor and action categories from elementary sensor readings and basic actions so that the necessary elements for solving a task are correctly perceived and manipulated. In reinforcement learning, a previous categorization process is needed to define sensor and action categories with special requirements that we analyze and that, in general, are difficult to achieve, especially in complex tasks such as those that arise when working with autonomous robots. We show how these special requirements should be relaxed and we sketch a reinforcement learning algorithm that uses a less restrictive form of sensory categorization than existing algorithms. Additionally, we show how a given sensory categorization can be improved so that it better fits the demands of the previous algorithm. ; This work was supported by the project 'Navegación basada en visión de robots autónomos en entornos no estructurados.' (070-724). ; Peer Reviewed


    Access

    Download


    Export, share and cite



    Title :

    Reinforcement learning and automatic categorization


    Contributors:

    Publication date :

    1999-01-01



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Learning Compositional Categorization Models

    Ommer, B. / Buhmann, J. M. | British Library Conference Proceedings | 2006


    Automatic categorization-based multi-stage pedestrian detection

    Yang, Kai / Du, Eliza Yingzi / Jiang, Pingge et al. | IEEE | 2012


    Efficient dictionary learning for visual categorization

    Tang, J. / Shao, L. / Li, X. | British Library Online Contents | 2014


    Automatic navigation using deep reinforcement learning

    BALAKRISHNAN KAUSHIK / NARAYANAN PRAVEEN / LAKEHAL-AYAT MOHSEN | European Patent Office | 2023

    Free access

    Automatic Navigation Using Deep Reinforcement Learning

    BALAKRISHNAN KAUSHIK / NARAYANAN PRAVEEN / LAKEHAL-AYAT MOHSEN | European Patent Office | 2019

    Free access