--- abstract: |- Evolutionary Robotics is a promising approach to automatically build efficient controllers using stochastic optimization techniques. However, works in this area are often confronted to complex environments where even simple tasks cannot be achieved. In the scope of this paper, we propose an approach based on explicit problem decomposition and dynamic environment shaping to ease the learning task. altloc: - http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/bredeche.pdf - http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/epirob05d.pdf chapter: ~ commentary: ~ commref: ~ confdates: 'July 22-24, 2005' conference: 'Fifth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems' confloc: 'Nara, Japan' contact_email: ~ creators_id: [] creators_name: - family: Bredeche given: Nicolas honourific: '' lineage: '' - family: Hugues given: Louis honourific: '' lineage: '' date: 2005 date_type: published datestamp: 2006-07-23 department: ~ dir: disk0/00/00/49/89 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Berthouze given: Luc honourific: '' lineage: '' - family: Kaplan given: Frédéric honourific: '' lineage: '' - family: Kozima given: Hideki honourific: '' lineage: '' - family: Yano given: Hiroyuki honourific: '' lineage: '' - family: Konczak given: Jürgen honourific: '' lineage: '' - family: Metta given: Giorgio honourific: '' lineage: '' - family: Nadel given: Jacqueline honourific: '' lineage: '' - family: Sandini given: Giulio honourific: '' lineage: '' - family: Stojanov given: Georgi honourific: '' lineage: '' - family: Balkenius given: Christian honourific: '' lineage: '' eprint_status: archive eprintid: 4989 fileinfo: /style/images/fileicons/application_pdf.png;/4989/1/bredeche.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: 'evolutionary robotics, developmental robot, task decomposition, dynamic fitness' lastmod: 2011-03-11 08:56:31 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 137-138 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 17:05:51 subjects: - comp-sci-mach-learn - comp-sci-robot succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: |- Speeding up Learning with Dynamic Environment Shaping in Evolutionary Robotics type: confposter userid: 3507 volume: 123