510 14 752 2 2490 document 752 learningUS.ps application/postscript 647621 2009-12-08 20:31:33 http://cogprints.org/510/1/learningUS.ps 2491 document 752 learningA4.ps application/postscript 647621 2009-12-08 20:31:33 http://cogprints.org/510/1/learningA4.ps 510 1 application/postscript application/postscript public

learningA4.ps

http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/4783 http://eprints.org/relation/haspreviewThumbnailVersion http://cogprints.org/id/document/4783 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/4783 10650 3 43056 document 10650 learning.pdf application/pdf 3927830 2009-12-08 20:31:33 http://cogprints.org/510/5/learning.pdf 510 5 5 application/pdf application/pdf public

learning.pdf

http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/4784 http://eprints.org/relation/haspreviewThumbnailVersion http://cogprints.org/id/document/4784 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/4784 http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/9799 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/9799 http://eprints.org/relation/hasIndexCodesVersion http://cogprints.org/id/document/9799 archive 192 disk0/00/00/05/10 1998-08-07 2011-03-11 08:54:01 2007-09-12 16:29:31 journalp show 0 Economists tend to represent learning as a procedure for estimating the parameters of the "correct" econometric model. We extend this approach by assuming that agents specify as well as estimate models. Learning thus takes the form of a dynamic process of developing models using an internal language of representation where expectations are formed by forecasting with the best current model. This introduces a distinction between the form and content of the internal models which is particularly relevant for boundedly rational agents. We propose a framework for such model development which use a combination of measures: the error with respect to past data, the complexity of the model, the cost of finding the model and a measure of the model's specificity The agent has to make various trade-offs between them. A utility learning agent is given as an example. http://www.cpm.mmu.ac.uk/cpmrep03.html Moss Scott Edmonds Bruce pub learning, bounded rationality, modelling, logic, noise, complexity, specificity economics, simulation 5-37 FALSE Cybernetics and Systems TRUE comp-sci-art-intel comp-sci-mach-learn phil-sci soc-psy 29 published 1994-11 public