2026-04-13T02:59:17Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/47952025-12-20T01:55:43Zcom_2072_6col_2072_452953

urn:hdl:10230/4795 Decision making in uncertain and changing environments Schlag, Karl Zapechelnyuk, Andriy adaptive learning experts distribution-free e-optimality hannan regret Microeconomics Statistics, Econometrics and Quantitative Methods 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. 2017-07-26T10:50:34Z 2017-07-26T10:50:34Z 2009-06-01 2017-07-23T02:12:36Z info:eu-repo/semantics/workingPaper Economics and Business Working Papers Series; 1160 L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons http://creativecommons.org/licenses/by-nc-nd/3.0/es/ info:eu-repo/semantics/openAccess