"Fully probabilistic control design in an adaptive critic framework" . . "Fully probabilistic control design in an adaptive critic framework"@en . "10" . . "10.1016/j.neunet.2011.06.006" . "Fully probabilistic control design in an adaptive critic framework" . . . "2"^^ . "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\u2013Leibler 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."@en . . . "0893-6080" . . . "Stochastic control design; Fully probabilistic design; Adaptive control; Adaptive critic"@en . . "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\u2013Leibler 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." . . "200501" . "Herzallah, R." . . "24" . . "RIV/67985556:_____/11:00364820!RIV12-AV0-67985556" . "[27C9D44110F9]" . "000297000300012" . . "Fully probabilistic control design in an adaptive critic framework"@en . . "GB - Spojen\u00E9 kr\u00E1lovstv\u00ED Velk\u00E9 Brit\u00E1nie a Severn\u00EDho Irska" . . "Neural Networks" . "8"^^ . . "P(GA102/08/0567), Z(AV0Z10750506)" . . . "RIV/67985556:_____/11:00364820" . "K\u00E1rn\u00FD, Miroslav" . . "1"^^ .