This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: 'One of the most interesting problems faced by Artificial Intelligence researchers is to reproduce a capability typical of living beings: that of learning to perform motor tasks, a problem known as skill acquisition. A very difficult purpose because the overwhole behavior of an agent is the result of quite a complex activity, involving sensory, planning and motor processing. In this paper, I present a novel approach for acquiring new skills, named Soft Teaching, that is characterized by a learning by experience process, in which an agent exploits a symbolic, qualitative description of the task to perform, that cannot, however, be used directly for control purposes. A specific Soft Teaching technique, named Symmetries, was implemented and tested against a continuous-domained version of well-known pole-balancing.' altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: April 23-25 conference: 'ECML-97, European Conference on Machine Learning' confloc: 'Prague, Czech Republic' contact_email: ~ creators_id: [] creators_name: - family: Baroglio given: Cristina honourific: '' lineage: '' date: 1997 date_type: published datestamp: 1999-01-07 department: ~ dir: disk0/00/00/05/28 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: van Someren given: Maarten honourific: '' lineage: '' - family: Widmer given: Gerhard honourific: '' lineage: '' eprint_status: archive eprintid: 528 fileinfo: /style/images/fileicons/application_postscript.png;/528/2/paper.ps 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: 'skill acquisition, knowledge-based feedback, adaptive agents, agent teaching, behaviour formation, qualitative knowledge use, symbolic/non-symbolic gap, hybrid systems, neural networks, reinforcement learning' lastmod: 2011-03-11 08:54:02 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 49-56 pubdom: FALSE publication: ~ publisher: Springer Verlag refereed: FALSE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:30:10 subjects: - behav-anal - cog-psy - comp-sci-art-intel - comp-sci-mach-learn - comp-sci-robot succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Exploiting qualitative knowledge to enhance skill acquisition type: confpaper userid: 194 volume: ~