Filtering Method for Linear and Non-Linear Stochastic Optimal Control Of Partially Observable Systems
Abstract
This paper studies two linear methods for linear and non-linear stochastic optimal control of
partially observable (SOCP) problems. At rst introduce the general form of a SOCP problem and state
it in a matrix functional form. A SOCP problem has a minimization payoff function and two dynamic
processes which are state and observation processes. In this study presented a deterministic method to
nd the control factor named feedback control and stated a modied complete proof of control optimality
in a general SOCP problem. After nding the optimal control factor, it should be substituted in the state
process to make the partially observable system. So introduce a linear ltering method to solve the related
partially observable system with complete details. Finally, presented a heuristic method in discrete form
for estimating non-linear SOCP problems and stated examples to evaluate the performance of introducing
methods.
partially observable (SOCP) problems. At rst introduce the general form of a SOCP problem and state
it in a matrix functional form. A SOCP problem has a minimization payoff function and two dynamic
processes which are state and observation processes. In this study presented a deterministic method to
nd the control factor named feedback control and stated a modied complete proof of control optimality
in a general SOCP problem. After nding the optimal control factor, it should be substituted in the state
process to make the partially observable system. So introduce a linear ltering method to solve the related
partially observable system with complete details. Finally, presented a heuristic method in discrete form
for estimating non-linear SOCP problems and stated examples to evaluate the performance of introducing
methods.
Full Text:
PDFRefbacks
- There are currently no refbacks.