Login / Signup

A policy iteration algorithm for fixed point problems with nonexpansive operators.

Jean-Philippe ChancelierMarouen MessaoudAgnès Sulem
Published in: Math. Methods Oper. Res. (2007)
Keyphrases
  • fixed point
  • sufficient conditions
  • belief propagation
  • floating point
  • policy iteration
  • temporal difference learning
  • linear programming
  • real valued
  • fixed point theorem