Asymptotic properties of constrained Markov decision processes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1992

Asymptotic properties of constrained Markov decision processes

Abstract

We present in this paper several asymptotic properties of constrained Markov Decision Processes (MDPs) with a countable state space. We treat both the discounted and the expected average cost, with unbounded cost. We are interested in the convergence of finite horizon MDPs to the infinite horizon MDP, convergence of MDPs with a truncated state space to the problem with infinite state space, convergence of MDPs as the discount factor goes to a limit. In all these cases we establish the convergence of optimal values and policies. Moreover, based on the optimal policy for the limiting problem, we construct policies which are almost optimal for the other (approximating) problems.
Fichier principal
Vignette du fichier
RR-1598.pdf (286.45 Ko) Télécharger le fichier

Dates and versions

inria-00074962 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00074962 , version 1

Cite

Eitan Altman. Asymptotic properties of constrained Markov decision processes. [Research Report] RR-1598, INRIA. 1992. ⟨inria-00074962⟩
84 View
12517 Download

Share

Gmail Facebook Twitter LinkedIn More