Hierarchical algorithms for discounted and weighted Markov decision processes |
| |
Authors: | Abbad M. Daoui C. |
| |
Affiliation: | (1) Faculté des Sciences, B.P. 1014, Rabat, Marokko;(2) Faculté des Sciences et Techniques, B.P. 523, Béni-Mellal, Marokko |
| |
Abstract: | We consider a discrete time finite Markov decision process (MDP) with the discounted and weighted reward optimality criteria. In [1] the authors considered some decomposition of limiting average MDPs. In this paper, we use an analogous approach for discounted and weighted MDPs. Then, we construct some hierarchical decomposition algorithms for both discounted and weighted MDPs. |
| |
Keywords: | Discounted MDP Weighted MDP Decomposition Strongly Connected Classes Graph theory |
本文献已被 SpringerLink 等数据库收录! |
|