Showing math.PRShow all
2 papers · 1 filter
math.PR2025
On the Feinberg-Piunovskiy Theorem and its extension to chattering policies
Francois Dufour, Tomas Prieto-Rumeau
The Feinberg-Piunovskiy Theorem established in [14, Theorem 3.8] asserts that for a discrete-time uniformly absorbing and atomless Markov Decision Process (MDP) with Borel state sp…
math.PR2017
On the expected total reward with unbounded returns for Markov decision processes
François Dufour, Alexandre Genadot
We consider a discrete-time Markov decision process with Borel state and action spaces. The performance criterion is to maximize a total expected {utility determined by unbounded r…