Blackwell optimality in Markov decision processes with partial observation
Rosenberg, Dinah ; Solan, Eilon ; Vieille, Nicolas
Ann. Statist., Tome 30 (2002) no. 1, p. 1178-1193 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
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.
Publié le : 2002-08-14
Classification:  Blackwell optimality,  MDP,  partial observation,  60J20,  62C99 
@article{1031689022,
     author = {Rosenberg, Dinah and Solan, Eilon and Vieille, Nicolas},
     title = {Blackwell optimality in Markov decision processes with partial observation},
     journal = {Ann. Statist.},
     volume = {30},
     number = {1},
     year = {2002},
     pages = { 1178-1193},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1031689022}
}

Rosenberg, Dinah; Solan, Eilon; Vieille, Nicolas. Blackwell optimality in Markov decision processes with partial observation. Ann. Statist., Tome 30 (2002) no. 1, pp.  1178-1193. http://gdmltest.u-ga.fr/item/1031689022/