Decision Making in Uncertain and Changing Environments
Karl Schlag () and
No 19, Discussion Papers from Kyiv School of Economics
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.
Keywords: Adaptive learning; experts; distribution-free; epsilon-optimality; Hannan regret (search for similar items in EconPapers)
JEL-codes: C44 D81 D83 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-gth
Note: Under review in Review of Economic Studies
References: View references in EconPapers View complete reference list from CitEc
Citations View citations in EconPapers (1) Track citations by RSS feed
Downloads: (external link)
http://repec.kse.org.ua/pdf/KSE_dp19.pdf First version, June 2009 (application/pdf)
Working Paper: Decision Making in Uncertain and Changing Environments (2009)
Working Paper: Decision making in uncertain and changing environments (2009)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: http://EconPapers.repec.org/RePEc:kse:dpaper:19
Access Statistics for this paper
More papers in Discussion Papers from Kyiv School of Economics Contact information at EDIRC.
Series data maintained by Iryna Sobetska ().