Learning from Errors

Juan Enrique Martinez-Legaz () and Antoine Soubeyran ()

UFAE and IAE Working Papers from Unitat de Fonaments de l'Anàlisi Econòmica (UAB) and Institut d'Anàlisi Econòmica (CSIC)

Abstract: We present a model of learning in which agents learn from errors. If an action turns out to be an error, the agent rejects not only that action but also neighboring actions. We find that, keepng memory of his errors, under mild assumptions an acceptable solution is asymptotically reached. Moreover, one can take advantage of big errors for a faster learning.

Keywords: Learning; errors; fixed points; normal form games; best reply functions (search for similar items in EconPapers)
JEL-codes: D83 C72 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-gth
Date: 2003-01-21
View list of references

Downloads: (external link)
http://pareto.uab.es/wp/2003/55703.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:aub:autbar:557.03

Access Statistics for this paper

More papers in UFAE and IAE Working Papers from Unitat de Fonaments de l'Anàlisi Econòmica (UAB) and Institut d'Anàlisi Econòmica (CSIC)
Contact information at EDIRC.
Series data maintained by Xavier Vila ().