Adaptive critic methods for stochastic systems with input-dependent noise

Herzallah, Randa

doi:10.1016/j.automatica.2007.01.023

Cited by 20 publications

(46 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed controller has been obtained directly by ideally solving the adaptive critic problem. In contrast to how the adaptive critic problem is usually used so as to derive the control law, certainty equivalence is not assumed in the cautious adaptive critic controller [18]. The control law is derived by minimization of the performance index (23), but with the uncertainty of the model estimates taken into consideration by treating the predicted state vector or output of the system as random variables.…”

Section: Adaptive Critic Controlmentioning

confidence: 99%

“…+ variance{η}, the sub-optimal performance index given in Equation (23) is shown to be given by [18] J…”

Section: Adaptive Critic Controlmentioning

confidence: 99%

“…Critic methods usually assume the availability of a forward model when calculating the control law. The argument raised in [18] was that, although an approximation model is usually identified so as to represent the forward model of the plant, researchers in the adaptive critic field usually assume that the obtained forward model is accurate and ignore uncertainty of that model. Consequently, a cautious type adaptive critic controller which takes uncertainty of a models' estimate into consideration when calculating the control law was proposed.…”

Section: Adaptive Critic Controlmentioning

confidence: 99%

“…This comes from the fact that the adaptive critic methods are an approximation for dynamic programming which is currently the only mathematical formalism under which an optimal controller can be designed under uncertain conditions. The fact that (23) Recently Herzallah [18] has proposed a new control algorithm for the adaptive critic networks which takes into consideration model uncertainty. Critic methods usually assume the availability of a forward model when calculating the control law.…”

Section: Adaptive Critic Controlmentioning

confidence: 99%

See 3 more Smart Citations

Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty

Herzallah

2011

IJMIC

Self Cite

View full text Add to dashboard Cite

Modern advances in technology have led to more complex manufacturing processes whose success centers on the ability to control these processes with a very high level of accuracy. Plant complexity inevitably leads to poor models that exhibit a high degree of parametric or functional uncertainty. The situation becomes even more complex if the plant to be controlled is characterized by a multi-valued function or even if it exhibits a number of modes of behavior during its operation. Since an intelligent controller is expected to operate and guarantee the best performance where complexity and uncertainty coexist and interact, control engineers and theorists have recently developed new control techniques under the framework of intelligent control to enhance the performance of the controller for more complex and uncertain plants. These techniques are based on incorporating model uncertainty. The new developed control algorithms for incorporating model uncertainty are proven to give more accurate control results under uncertain conditions. In this paper we survey some approaches that appear to be promising for enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty.

show abstract

Section: Adaptive Critic Controlmentioning

confidence: 99%

“…+ variance{η}, the sub-optimal performance index given in Equation (23) is shown to be given by [18] J…”

Section: Adaptive Critic Controlmentioning

confidence: 99%

Section: Adaptive Critic Controlmentioning

confidence: 99%

Section: Adaptive Critic Controlmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty

Herzallah

2011

IJMIC

Self Cite

View full text Add to dashboard Cite

show abstract

“…The control input can be calculated using Equation (34) once the critic network and system state density models become available. The implementation of this two stage optimisation method can be performed efficiently by utilising the modular approach constituting of functional modules and algorithmic modules (Ferrari and Stengel, 2004;Lendaris et al, 2002;Herzallah, 2007). The main functional modules are the action and critic networks.…”

Section: Generalised Nonlinear Probabilistic Control Algorithmmentioning

confidence: 99%

Fully probabilistic control for stochastic nonlinear control systems with input dependent noise

Herzallah

2015

Neural Networks

Self Cite

View full text Add to dashboard Cite

Robust controllers for nonlinear stochastic systems with functional uncertainties can be consistently designed using probabilistic control methods. In this paper a generalised probabilistic controller design for the minimisation of the Kullback-Leibler divergence between the actual joint probability density function (pdf) of the closed loop control system, and an ideal joint pdf is presented emphasising how the uncertainty can be systematically incorporated in the absence of reliable systems models. To achieve this objective all probabilistic models of the system are estimated from process data using mixture density networks (MDNs) where all the parameters of the estimated pdfs are taken to be state and control input dependent. Based on this dependency of the density parameters on the input values, explicit formulations to the construction of optimal generalised probabilistic controllers are obtained through the techniques of dynamic programming and adaptive critic methods. Using the proposed generalised probabilistic controller, the conditional joint pdfs can be made to follow the ideal ones. A simulation example is used to demonstrate the implementation of the algorithm and encouraging results are obtained.

show abstract

Adaptive Control and Signal Processing Literature Survey (No. 2)

2007

Adaptive Control & Signal

View full text Add to dashboard Cite

Adaptive critic methods for stochastic systems with input-dependent noise

Cited by 20 publications

References 8 publications

Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty

Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty

Fully probabilistic control for stochastic nonlinear control systems with input dependent noise

Adaptive Control and Signal Processing Literature Survey (No. 2)

Contact Info

Product

Resources

About