On the Expected Total Reward with Unbounded Returns for Markov Decision Processes
DUFOUR, François
Institut Polytechnique de Bordeaux [Bordeaux INP]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
Institut Polytechnique de Bordeaux [Bordeaux INP]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
GENADOT, Alexandre
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
DUFOUR, François
Institut Polytechnique de Bordeaux [Bordeaux INP]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
Institut Polytechnique de Bordeaux [Bordeaux INP]
Quality control and dynamic reliability [CQFD]
Institut de Mathématiques de Bordeaux [IMB]
GENADOT, Alexandre
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
< Reduce
Institut de Mathématiques de Bordeaux [IMB]
Quality control and dynamic reliability [CQFD]
Language
en
Article de revue
This item was published in
Applied Mathematics and Optimization. 2020, vol. 82, n° 2, p. 433-450
Springer Verlag (Germany)
English Abstract
We consider a discrete-time Markov decision process with Borel state and action spaces. The performance criterion is to maximize a total expected utility determined by unbounded return function. It is shown the existence ...Read more >
We consider a discrete-time Markov decision process with Borel state and action spaces. The performance criterion is to maximize a total expected utility determined by unbounded return function. It is shown the existence of optimal strategies under general conditions allowing the reward function to be unbounded both from above and below and the action sets available at each step to the decision maker to be not necessarily compact. To deal with unbounded reward functions, a new characterization for the weak convergence of probability measures is derived. Our results are illustrated by examples.Read less <
English Keywords
Markov decision processes
Expected total reward
Unbounded return
Weak convergence of measure
Origin
Hal imported