Online policy iteration based algorithms to solve the continuous-time infinite horizon optimal control problem

Authors :: Kyriakos G. Vamvoudakis
Draguna Vrabie
Frank L. Lewis
Source :: ADPRL
Publication Year :: 2009
Publisher :: IEEE, 2009.
Abstract: In this paper we discuss two online algorithms based on policy iterations for learning the continuous-time (CT) optimal control solution when nonlinear systems with infinite horizon quadratic cost are considered.

Subjects :: Nonlinear system
Mathematical optimization
Artificial neural network
Convergence (routing)
Stability (learning theory)
Approximation algorithm
Infinite horizon
Online algorithm
Optimal control
Mathematics

Database :: OpenAIRE
Journal :: 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning
Accession number :: edsair.doi...........4543a1fa709ec7c4229fab86d5e1b570

Tools