On the Expected Total Reward with Unbounded Returns for Markov Decision Processes
Idioma
en
Article de revue
Este ítem está publicado en
Applied Mathematics and Optimization. 2020, vol. 82, n° 2, p. 433-450
Springer Verlag (Germany)
Resumen en inglés
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 ...Leer más >
Palabras clave en inglés
Markov decision processes
Expected total reward
Unbounded return
Weak convergence of measure