Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
Langue
en
Article de revue
Ce document a été publié dans
Stochastics: An International Journal of Probability and Stochastic Processes. 2015, vol. 87, n° 2, p. 273 - 307
Taylor & Francis: STM, Behavioural Science and Public Health Titles
Résumé en anglais
We consider a discrete-time Markov decision process with Borel state and action spaces, and possibly unbounded cost function. We assume that the Markov transition kernel is absolutely continuous with respect to some ...Lire la suite >
Mots clés en anglais
Wasserstein distance
Concentration inequalities
Approximation of the optimal value and an optimal policy
Long-run average cost
Markov decision processes