| Issue |
ESAIM: COCV
Volume 30, 2024
|
|
|---|---|---|
| Article Number | 5 | |
| Number of page(s) | 18 | |
| DOI | https://doi.org/10.1051/cocv/2024002 | |
| Published online | 09 February 2024 | |
Absorbing Markov decision processes
1
Institut Polytechnique de Bordeaux; INRIA Bordeaux Sud Ouest, Team: ASTRAL; IMB, Institut de Mathématiques de Bordeaux, Université de Bordeaux, France
2
Statistics Department, UNED, Madrid, Spain
* Corresponding author: tprieto@ccia.uned.es
Received:
19
September
2023
Accepted:
30
December
2023
In this paper, we study discrete-time absorbing Markov Decision Processes (MDP) with measurable state space and Borel action space with a given initial distribution. For such models, solutions to the characteristic equation that are not occupation measures may exist. Several necessary and sufficient conditions are provided to guarantee that any solution to the characteristic equation is an occupation measure. Under the so-called continuity-compactness conditions, we first show that a measure is precisely an occupation measure if and only if it satisfies the characteristic equation and an additional absolute continuity condition. Secondly, it is shown that the set of occupation measures is compact in the weak-strong topology if and only if the model is uniformly absorbing. Several examples are provided to illustrate our results.
Mathematics Subject Classification: 91A10 / 91A15
Key words: Markov decision processes / absorbing model / occupation measures / characteristic equation / phantom measures / compactness of the set of occupation measures
© The authors. Published by EDP Sciences, SMAI 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.