Hierarchical algorithms for discounted and weighted Markov decision processes
- 53 Downloads
We consider a discrete time finite Markov decision process (MDP) with the discounted and weighted reward optimality criteria. In  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.
KeywordsDiscounted MDP Weighted MDP Decomposition Strongly Connected Classes Graph theory
Unable to display preview. Download preview PDF.