Extreme occupation measures in Markov decision processes with an absorbing state.



Piunovskiy, Alexey ORCID: 0000-0002-9683-4856 and Zhang, Yi ORCID: 0000-0002-3200-6306
(2024) Extreme occupation measures in Markov decision processes with an absorbing state. SIAM Journal on Control and Optimization, 62 (1). pp. 65-90. ISSN 0363-0129, 1095-7138

[thumbnail of SICONfinalForProof.pdf] Text
SICONfinalForProof.pdf - Author Accepted Manuscript
Available under License Creative Commons Attribution.

Download (367kB) | Preview

Abstract

In this paper, we consider a Markov decision process (MDP) with a Borel state space X U {∆}, where ∆ is an absorbing state (cemetery), and a Borel action space A. We consider the space of finite occupation measures restricted on X X A and the extreme points in it. It is possible that some strategies have infinite occupation measures. Nevertheless, we prove that every finite extreme occupation measure is generated by a deterministic stationary strategy. Then, for this MDP, we consider a constrained problem with total undiscounted criteria and J constraints, where the cost functions are nonnegative. By assumption, the strategies inducing infinite occupation measures are not optimal. Then our second main result is that, under mild conditions, the solution to this constrained MDP is given by a mixture of no more than J + 1 occupation measures generated by deterministic stationary strategies.

Item Type: Article
Uncontrolled Keywords: 4901 Applied Mathematics, 5108 Quantum Physics, 49 Mathematical Sciences, 51 Physical Sciences
Divisions: Faculty of Science & Engineering > School of Physical Sciences
Depositing User: Symplectic Admin
Date Deposited: 11 Jan 2024 08:41
Last Modified: 24 Jan 2026 04:43
DOI: 10.1137/23M1572398
Related Websites:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3177797
Disclaimer: The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.