Advertisement

The Policy Iteration Algorithm for PDMPs

  • Oswaldo Luiz do Valle CostaEmail author
  • François Dufour
Chapter
  • 610 Downloads
Part of the SpringerBriefs in Mathematics book series (BRIEFSMATH)

Abstract

The main goal of this chapter is to apply the so-called policy iteration algorithm (PIA) for the long-run average continuous control problem of PDMPs. The first step in this direction is to derive some important properties of a pseudo-Poisson equation associated with the problem.

Keywords

Policy Iteration Algorithm (PIA) Average Control Problem Shift Control Strategy Optimality Equation Geometric Convergence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Copyright information

© Oswaldo Luiz do Valle Costa, François Dufour 2013

Authors and Affiliations

  • Oswaldo Luiz do Valle Costa
    • 1
    Email author
  • François Dufour
    • 2
  1. 1.Department of Telecommunications and Control EngineeringUniversity of São PauloSão PauloBrazil
  2. 2.Universite Bordeaux 1, Institut de Mathématiques de BordeauxInstitut Polytechnique de BordeauxTalence cedexFrance

Personalised recommendations