Blackwell optimality in Markov decision processes with partial observation

Blackwell optimality in Markov decision processes with partial observation

0.00 Avg rating0 Votes
Article ID: iaor20042777
Country: United States
Volume: 30
Issue: 4
Start Page Number: 1178
End Page Number: 1193
Publication Date: Aug 2002
Journal: Annals of Statistics
Authors: , ,
Keywords: markov processes
Abstract:

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.

Reviews

Required fields are marked *. Your email address will not be published.