Reinforcement learning (RL) is a valuable learning method when the systems require a selection of control actions whose consequences emerge over long periods for which input-output data are not available. In most combinations of fuzzy systems and RL, the environment is considered to be deterministic. In many problems, however, the consequence of an action may be uncertain or stochastic in nature. In this paper, we propose a novel RL approach to combine the universal-function-approximation capability of fuzzy systems with consideration of probability distributions over possible consequences of an action. The proposed generalized probabilistic fuzzy RL (GPFRL) method is a modified version of the actor-critic (AC) learning architecture. The learning is enhanced by the introduction of a probability measure into the learning structure, where an incremental gradient-descent weight-updating algorithm provides convergence. Our results show that the proposed approach is robust under probabilistic uncertainty while also having an enhanced learning speed and good overall performance.


    Access

    Download


    Export, share and cite



    Title :

    Systems control with generalized probabilistic fuzzy-reinforcement learning


    Contributors:
    Hinojosa, J. (author) / Nefti, S. (author) / Kaymak, U. (author)

    Publication date :

    2011-01-01


    Remarks:

    Hinojosa , J , Nefti , S & Kaymak , U 2011 , ' Systems control with generalized probabilistic fuzzy-reinforcement learning ' , IEEE Transactions on Fuzzy Systems , vol. 19 , no. 1 , pp. 51-64 . https://doi.org/10.1109/TFUZZ.2010.2081994



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    DDC:    006 / 629



    Reinforcement learning for temporal logic control synthesis with probabilistic satisfaction guarantees

    Hasanbeig, M / Kantaros, Y / Abate, A et al. | BASE | 2019

    Free access

    Fuzzy Reinforcement Learning for System of Systems (SOS)

    Berenji, Hamid / Naghibzadeh, Maryam | AIAA | 2009


    Fuzzy Reinforcement Learning for System of Systems (SOS)

    Berenji, H. / Naghibzadeh, M. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 2009


    Adaptive fuzzy control of satellite attitude by reinforcement learning

    Buijtenen, W.M. van / Schram, G. / Babuska, R. et al. | Tema Archive | 1998


    Adaptive fuzzy control for rendezvous and docking by reinforcement learning

    Mulder, J. / Bennis, R. / Chu, Q. et al. | AIAA | 2001