Uniform value in Dynamic Programming

Jérôme Renault (1)

1 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision

We consider dynamic programming problems and give sufficient conditions for the existence of the uniform value. As a consequence, we obtain an existence result when the state space is precompact, payoffs are uniformly continuous and the transition correspondence is non expansive. We also apply our results to Markov decision processes and obtain a few generalizations.

Mots clés: Uniform value; Dynamic programming; Markov decision processes; Blackwell optimality; average payoffs; limit values; precompact state space; non expansive correspondence.; non expansive correspondence

Domaines: Optimisation et contrôle [math.OC]

Jérôme Renault. Uniform value in Dynamic Programming. 2008. ⟨hal-00265257v1⟩