WOS: 000449440400001 ; In this work, a Nadaraya-Watson kernel based learning system which owns general regression neural network topology is adapted to Q learning method to evaluate a quick and efficient action selection policy for reinforcement learning problems. By means of the proposed method Q value function is generalized and learning speed of Q agent is accelerated. The training data of the developed neural network are obtained by a standard Q learning agent on closed-loop simulation system. The efficiency of the proposed method is tested on popular reinforcement learning benchmarks and its performance is compared with other popular regression methods and Q-learning utilized methods. QLRNN increased the learning performance and it learns faster than other methods on selected benchmarks. Test results showed the efficiency and the importance of the proposed network.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Q Learning Regression Neural Network



    Erscheinungsdatum :

    2018-01-01


    Anmerkungen:

    431



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    006 / 629



    Public Bicycle Prediction Based on Generalized Regression Neural Network

    Yang, Min / Guang, Yingnan / Zhang, Xuedan | British Library Conference Proceedings | 2015