--- abstract: 'This paper presents the mechanism of Intelligent Adaptive Curiosity. This is a drive which pushes the robot towards situations in which it maximizes its learning progress. It makes the robot focus on situations which are neither too predictable nor too unpredictable. This mechanism is a source of self-development for the robot: the complexity of its activity autonomously increases. Indeed, we show that it first spends time in situations which are easy to learn, then shifts progressively its attention to situations of increasing difficulty, avoiding situations in which nothing can be learnt.' altloc: - http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS117/oudeyer.pdf chapter: ~ commentary: ~ commref: ~ confdates: 'August 25-27, 2004' conference: 'Fourth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems' confloc: 'Genoa, Italy' contact_email: ~ creators_id: [] creators_name: - family: Oudeyer given: Pierre-Yves honourific: '' lineage: '' date: 2004 date_type: published datestamp: 2005-04-14 department: ~ dir: disk0/00/00/41/44 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Berthouze given: Luc honourific: '' lineage: '' - family: Kozima given: Hideki honourific: '' lineage: '' - family: Prince given: Christopher G. honourific: '' lineage: '' - family: Sandini given: Giulio honourific: '' lineage: '' - family: Stojanov given: Georgi honourific: '' lineage: '' - family: Metta given: Giorgio honourific: '' lineage: '' - family: Balkenius given: Christian honourific: '' lineage: '' eprint_status: archive eprintid: 4144 fileinfo: /style/images/fileicons/application_pdf.png;/4144/1/oudeyer.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: 'self-development, artifical value system, ensemble of experts, robotic learning' lastmod: 2011-03-11 08:55:52 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 127-130 pubdom: FALSE publication: ~ publisher: Lund University Cognitive Studies refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 12 series: ~ source: ~ status_changed: 2007-09-12 16:56:07 subjects: - comp-sci-mach-learn - comp-sci-art-intel - comp-sci-robot succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: 'Intelligent Adaptive Curiosity: a source of Self-Development' type: confpaper userid: 3507 volume: 117