pith. sign in

arxiv: 1806.00190 · v7 · pith:3SALF5XRnew · submitted 2018-06-01 · 🧮 math.OC

Constrained discounted Markov decision processes with Borel state spaces

classification 🧮 math.OC
keywords functionsrewardborelcmdpsconstraineddecisiondiscountedgeneral
0
0 comments X
read the original abstract

We study discrete-time discounted constrained Markov decision processes (CMDPs) on Borel spaces with unbounded reward functions. In our approach the transition probability functions are weakly or set-wise continuous. The reward functions are upper semicontinuous in state-action pairs or semicontinuous in actions. Our aim is to study models with unbounded reward functions, which are often encountered in applications, e.g., in consumption/investment problems. We provide some general assumptions under which the optimization problems in CMDPs are solvable in the class of stationary randomized policies. Then, we indicate that if the initial distribution and transition probabilities are non-atomic, then using a general purification result of Feinberg and Piunovskiy, stationary optimal policies can be deterministic. Our main results are illustrated by five examples.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.