Output Feedback Q-Learning for Linear-Quadratic Discrete-Time Finite-Horizon Control Problems
Giuseppe C. Calafiore, Corrado Possieri
Abstract
An algorithm is proposed to determine output feedback policies that solve finite-horizon linear-quadratic (LQ) optimal control problems without requiring knowledge of the system dynamical matrices. To reach this goal, the Q -factors arising from finite-horizon LQ problems are first characterized in the state feedback case. It is then shown how they can be parameterized as functions of the input-output vectors. A procedure is then proposed for estimating these functions from input/output data and using these estimates for computing the optimal control via the measured inputs and outputs.
Topics & Concepts
Parameterized complexityControl theory (sociology)HorizonLinear-quadratic regulatorOptimal controlState (computer science)Control (management)Output feedbackQuadratic equationMathematicsTime horizonLinear-quadratic-Gaussian controlDiscrete time and continuous timeController (irrigation)Linear systemComputer scienceMathematical optimizationAlgorithmArtificial intelligenceMathematical analysisGeometryAgronomyStatisticsBiologyAdaptive Dynamic Programming ControlAdaptive Control of Nonlinear SystemsAdvanced Control Systems Optimization