Dynamic programming for variable discounted Markov decision problems

Authors
Della Vecchia, Eugenio; Di Marco, Silvia; Vidal, Fernando
Publication Year
2014
Language
English
Format
conference paper
Status
Published version
Description
We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.
Sociedad Argentina de Informática e Investigación Operativa (SADIO)
Subject
Ciencias Informáticas
dynamic programming
Programming Environments
Decision problems
Markov decision processes
variable discount factor
Access level
Open access
License
Creative Commons Attribution 3.0 Unported (CC BY 3.0)
Repository
SEDICI (UNLP)
Institution
Universidad Nacional de La Plata
OAI Identifier
oai:sedici.unlp.edu.ar:10915/41704