Blackwell optimality in Markov decision processes with partial observation

Dinah Rosenberg (1) , Nicolas Vieille (2) , Eilon Solan (3)

1 LAGA - Laboratoire Analyse, Géométrie et Applications
2 GREGH - Groupement de Recherche et d'Etudes en Gestion à HEC
3 TAU - Tel Aviv University

A Blackwell $\epsilon$-optimal strategy in a Markov Decision Process is a strategy that is $\epsilon$-optimal for every discount factor sufficiently close to 1. We prove the existence of Blackwell $\epsilon$-optimal strategies in finite Markov Decision Processes with partial observation.

Keywords: Blackwell optimality; MDP; partial observation

Domains: Economy and decision science

Dinah Rosenberg, Nicolas Vieille, Eilon Solan. Blackwell optimality in Markov decision processes with partial observation. Annals of Statistics, 2002, Vol.30,n°4, pp.1178-1193. ⟨10.1214/aos/1031689022⟩. ⟨hal-00464998⟩