Decision making in uncertain and changing environments
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Schlag, Karlca
- dc.contributor.author Zapechelnyuk, Andriyca
- dc.contributor.other Universitat Pompeu Fabra. Departament d'Economia i Empresa
- dc.date.accessioned 2017-07-26T10:50:34Z
- dc.date.available 2017-07-26T10:50:34Z
- dc.date.issued 2009-06-01
- dc.date.modified 2017-07-23T02:12:36Z
- dc.description.abstract We consider an agent who has to repeatedly make choices in an uncertain and changing environment, who has full information of the past, who discounts future payoffs, but who has no prior. We provide a learning algorithm that performs almost as well as the best of a given finite number of experts or benchmark strategies and does so at any point in time, provided the agent is sufficiently patient. The key is to find the appropriate degree of forgetting distant past. Standard learning algorithms that treat recent and distant past equally do not have the sequential epsilon optimality property.
- dc.format.mimetype application/pdfca
- dc.identifier https://econ-papers.upf.edu/ca/paper.php?id=1160
- dc.identifier.uri http://hdl.handle.net/10230/4795
- dc.language.iso eng
- dc.relation.ispartofseries Economics and Business Working Papers Series; 1160
- dc.rights L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/es/
- dc.subject.keyword adaptive learning
- dc.subject.keyword experts
- dc.subject.keyword distribution-free
- dc.subject.keyword e-optimality
- dc.subject.keyword hannan regret
- dc.subject.keyword Microeconomics
- dc.subject.keyword Statistics, Econometrics and Quantitative Methods
- dc.title Decision making in uncertain and changing environmentsca
- dc.type info:eu-repo/semantics/workingPaper