Blackwell Optimality in Markov Decision Processes with Partial Observation

 

Dinah Rosenberg, Eilon Solan and Nicolas Vieille

 

The Annals of Statistics 30 (2002).

 

A Blackwell e-optimal strategy in a Markov Decision Process is a strategy that is e-optimal for every discount factor sufficiently close to 1.

 

We prove the existence of Blackwell e-optimal strategies in finite Markov Decision Processes with partial observation. Extensions to more general cases are also provided.