On the Expected Total Reward with Unbounded Returns for Markov Decision Processes
| hal.structure.identifier | Institut Polytechnique de Bordeaux [Bordeaux INP] | |
| hal.structure.identifier | Quality control and dynamic reliability [CQFD] | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | DUFOUR, François | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| hal.structure.identifier | Quality control and dynamic reliability [CQFD] | |
| dc.contributor.author | GENADOT, Alexandre | |
| dc.date.accessioned | 2024-04-04T03:03:19Z | |
| dc.date.available | 2024-04-04T03:03:19Z | |
| dc.date.issued | 2020 | |
| dc.identifier.issn | 0095-4616 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/193059 | |
| dc.description.abstractEn | We consider a discrete-time Markov decision process with Borel state and action spaces. The performance criterion is to maximize a total expected utility determined by unbounded return function. It is shown the existence of optimal strategies under general conditions allowing the reward function to be unbounded both from above and below and the action sets available at each step to the decision maker to be not necessarily compact. To deal with unbounded reward functions, a new characterization for the weak convergence of probability measures is derived. Our results are illustrated by examples. | |
| dc.language.iso | en | |
| dc.publisher | Springer Verlag (Germany) | |
| dc.subject.en | Markov decision processes | |
| dc.subject.en | Expected total reward | |
| dc.subject.en | Unbounded return | |
| dc.subject.en | Weak convergence of measure | |
| dc.title.en | On the Expected Total Reward with Unbounded Returns for Markov Decision Processes | |
| dc.type | Article de revue | |
| dc.identifier.doi | 10.1007/s00245-018-9533-6 | |
| dc.subject.hal | Mathématiques [math]/Optimisation et contrôle [math.OC] | |
| bordeaux.journal | Applied Mathematics and Optimization | |
| bordeaux.page | 433-450 | |
| bordeaux.volume | 82 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.issue | 2 | |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-01953985 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-01953985v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Applied%20Mathematics%20and%20Optimization&rft.date=2020&rft.volume=82&rft.issue=2&rft.spage=433-450&rft.epage=433-450&rft.eissn=0095-4616&rft.issn=0095-4616&rft.au=DUFOUR,%20Fran%C3%A7ois&GENADOT,%20Alexandre&rft.genre=article |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||