--- 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." altloc: - http://www.cpm.mmu.ac.uk/cpmrep03.html chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Moss given: Scott honourific: '' lineage: '' - family: Edmonds given: Bruce honourific: '' lineage: '' date: 1994-11 date_type: published datestamp: 1998-08-07 department: ~ dir: disk0/00/00/05/10 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 510 fileinfo: /style/images/fileicons/application_postscript.png;/510/1/learningA4.ps|/style/images/fileicons/application_pdf.png;/510/5/learning.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: 'learning, bounded rationality, modelling, logic, noise, complexity, specificity economics, simulation' lastmod: 2011-03-11 08:54:01 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 5-37 pubdom: FALSE publication: Cybernetics and Systems publisher: ~ refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 14 series: ~ source: ~ status_changed: 2007-09-12 16:29:31 subjects: - comp-sci-art-intel - comp-sci-mach-learn - phil-sci - soc-psy succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Modelling Learning as Modelling type: journalp userid: 192 volume: 29