creators_name: Moss, Scott
creators_name: Edmonds, Bruce
type: journalp
datestamp: 1998-08-07
lastmod: 2011-03-11 08:54:01
metadata_visibility: show
title: Modelling Learning as Modelling
ispublished: pub
subjects: comp-sci-art-intel
subjects: comp-sci-mach-learn
subjects: phil-sci
subjects: soc-psy
full_text_status: public
keywords: learning, bounded rationality, modelling, logic, noise, complexity, specificity economics, simulation
abstract: 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.
date: 1994-11
date_type: published
publication: Cybernetics and Systems
volume: 29
pagerange: 5-37
refereed: TRUE
citation:   Moss, Scott and Edmonds, Bruce  (1994) Modelling Learning as Modelling.  [Journal (Paginated)]     
document_url: http://cogprints.org/510/1/learningA4.ps
document_url: http://cogprints.org/510/5/learning.pdf