Abstract
AbstractIn this paper, we prove the following assertion for an absorbing Markov decision process (MDP) with the given initial distribution, which is also assumed to be semi-continuous: the continuity of the projection mapping from the space of strategic measures to the space of occupation measures, both endowed with their weak topologies, is equivalent to the MDP model being uniformly absorbing. An example demonstrates, among other interesting scenarios, that for an absorbing (but not uniformly absorbing) semi-continuous MDP with the given initial distribution, the space of occupation measures can fail to be compact in the weak topology.
Publisher
Springer Science and Business Media LLC
Reference20 articles.
1. Altman, E.: Constrained Markov Decision Processes. Chapman and Hall/CRC, Boca Raton (1999)
2. Bertsekas, D., Shreve, S.: Stochastic Optimal Control. Academic Press, New York (1978)
3. Bogachev, V.: Measure Theory, vol. 2. Springer, Berlin (2007)
4. Bogachev, V.: Weak Convergence of Measures. American Mathematical Society, Providence (2018)
5. Cavazos-Cadena, R., Hernández-Lerma: Equivalence of Lyapunov stability criteria in a class of Markov decision processes. Appl. Math. Optim. 26, 113–137 (1992)
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献