Abstract.
In this paper, Weighted reward Perturbed Markov Decision Processes with finite state and countable action spaces (semi-infinite WMDP for short) are considered. The ”weighted reward” refers to appropriately normalized convex combination of the discounted and the long-run average reward criteria. This criterion allows the controller to trade-off short-term rewards versus long-run rewards. In every application where both the discounted and the long-run average criteria have been proposed in the past, there is clearly a rationale for considering the weighted criterion. Of course, as with all Markov decision models, the standard weighted criterion model assumes that all the transition probabilities are known precisely. Since, in most applications this would not be the case, we consider the perturbed version of the weighted reward model. In the case of perturbations, we prove that for many models a nearly optimal strategy can be found in the class of relatively “simple ultimately deterministic” strategies. These are strategies which behave just like deterministic stationary strategies, after a certain point of time.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding author
Additional information
Manuscript received: September 2003/Final version received: January 2004
Rights and permissions
About this article
Cite this article
Abbad, M., Rahhali, K. Semi-infinite weighted Markov decision processes with perturbation. Math Meth Oper Res 60, 251–265 (2004). https://doi.org/10.1007/s001860400363
Issue Date:
DOI: https://doi.org/10.1007/s001860400363