Presentado al ICINCO 2010 celebrado en Funchal (Portugal) del 15 al 18 de junio. ; The successful application of Reinforcement Learning (RL) techniques to robot control is limited by the fact that, in most robotic tasks, the state and action spaces are continuous, multidimensional, and in essence, too large for conventional RL algorithms to work. The well known curse of dimensionality makes infeasible using a tabular representation of the value function, which is the classical approach that provides convergence guarantees. When a function approximation technique is used to generalize among similar states, the convergence of the algorithm is compromised, since updates unavoidably affect an extended region of the domain, that is, some situations are modified in a way that has not been really experienced, and the update may degrade the approximation. We propose a RL algorithm that uses a probability density estimation in the joint space of states, actions and Q-values as a means of function approximation. This allows us to devise an updating approach that, taking into account the local sampling density, avoids an excessive modification of the approximation far from the observed sample. ; This work was supported by the project 'CONSOLIDER-INGENIO 2010 Multimodal interaction in pattern recognition and computer vision' (V-00069). This research was partially supported by Consolider Ingenio 2010, project CSD2007-00018. ; Peer Reviewed


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement learning for robot control using probability density estimations


    Beteiligte:

    Erscheinungsdatum :

    2010-01-01


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Residual reinforcement learning for robot control

    Johannink, Tobias / Bahl, Shikhar / Nair, Ashvin et al. | BASE | 2019

    Freier Zugriff

    Conflict Probability Estimations Based on Geometrical and Bayesian Approaches

    Bashllari, Alfred / Kaciroti, Niko / Nace, Dritan et al. | IEEE | 2007


    Coordinated Multi-Robot Exploration using Reinforcement Learning

    Mete, Atharva / Mouhoub, Malek / Farid, Ali Moltajaei | IEEE | 2023


    Reinforcement learning for robot soccer

    Riedmiller, M. | British Library Online Contents | 2009