Open Access
August 2002 Blackwell optimality in Markov decision processes with partial observation
Dinah Rosenberg, Eilon Solan, Nicolas Vieille
Ann. Statist. 30(4): 1178-1193 (August 2002). DOI: 10.1214/aos/1031689022


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.


Download Citation

Dinah Rosenberg. Eilon Solan. Nicolas Vieille. "Blackwell optimality in Markov decision processes with partial observation." Ann. Statist. 30 (4) 1178 - 1193, August 2002.


Published: August 2002
First available in Project Euclid: 10 September 2002

zbMATH: 1103.90402
MathSciNet: MR1926173
Digital Object Identifier: 10.1214/aos/1031689022

Primary: 60J20 , 62C99

Keywords: Blackwell optimality , MDP , partial observation

Rights: Copyright © 2002 Institute of Mathematical Statistics

Vol.30 • No. 4 • August 2002
Back to Top