Detecting optimal and non-optimal actions in average-cost Markov decision processes

Jean B. LasserreJournal of Applied Probability 1994 · DOI

Abstract

We present two sufficient conditions for detection of optimal and non-optimal actions in (ergodic) average-cost MDPs. They are easily interpreted and can be implemented as detection tests in both policy iteration and linear programming methods. An efficient implementation of a recent new policy iteration scheme is discussed.
BibTeX
@article{lasserre1994detecting,
  author = {Jean B. Lasserre},
  title = {{Detecting optimal and non-optimal actions in average-cost Markov decision processes}},
  journal = {Journal of Applied Probability},
  year = {1994},
  doi = {10.2307/3215322},
}

Loading related content...

Figure