Počet záznamů: 1

Fully probabilistic control design in an adaptive critic framework

  1. 1.
    0364820 - UTIA-B 2012 RIV GB eng J - Článek v odborném periodiku
    Herzallah, R. - Kárný, Miroslav
    Fully probabilistic control design in an adaptive critic framework.
    Neural Networks. Roč. 24, č. 10 (2011), s. 1128-1135 ISSN 0893-6080
    Grant CEP: GA ČR GA102/08/0567
    Výzkumný záměr: CEZ:AV0Z10750506
    Klíčová slova: Stochastic control design * Fully probabilistic design * Adaptive control * Adaptive critic
    Kód oboru RIV: BC - Teorie a systémy řízení
    Impakt faktor: 2.182, rok: 2011
    http://library.utia.cas.cz/separaty/2011/AS/karny-0364820.pdf http://library.utia.cas.cz/separaty/2011/AS/karny-0364820.pdf

    Optimal stochastic controller pushes the closed-loop behavior as close as possible to the desired one. The fully probabilistic design (FPD) uses probabilistic description of the desired closed loop and minimizes Kullback–Leibler divergence of the closed-loop description to the desired one. Practical exploitation of the fully probabilistic design control theory continues to be hindered by the computational complexities involved in numerically solving the associated stochastic dynamic programming problem; in particular, very hard multivariate integration and an approximate interpolation of the involved multivariate functions. This paper proposes a new fully probabilistic control algorithm that uses the adaptive critic methods to circumvent the need for explicitly evaluating the optimal value function, thereby dramatically reducing computational requirements. This is a main contribution of this paper.
    Trvalý link: http://hdl.handle.net/11104/0200201