4989 12 3149 3 16584 document 3149 bredeche.pdf application/pdf 3122953 2009-12-08 20:56:19 http://cogprints.org/4989/1/bredeche.pdf 4989 1 application/pdf application/pdf en public

bredeche.pdf

http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/6501 http://eprints.org/relation/haspreviewThumbnailVersion http://cogprints.org/id/document/6501 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/6501 http://eprints.org/relation/hasVolatileVersion http://cogprints.org/id/document/8282 http://eprints.org/relation/hasVersion http://cogprints.org/id/document/8282 http://eprints.org/relation/hasIndexCodesVersion http://cogprints.org/id/document/8282 archive 3507 disk0/00/00/49/89 2006-07-23 2011-03-11 08:56:31 2007-09-12 17:05:51 confposter show 0 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. http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/bredeche.pdf http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/epirob05d.pdf Bredeche Nicolas Hugues Louis July 22-24, 2005 Fifth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems Nara, Japan Berthouze Luc Kaplan Frédéric Kozima Hideki Yano Hiroyuki Konczak Jürgen Metta Giorgio Nadel Jacqueline Sandini Giulio Stojanov Georgi Balkenius Christian pub evolutionary robotics, developmental robot, task decomposition, dynamic fitness 137-138 FALSE Lund University Cognitive Studies TRUE comp-sci-mach-learn comp-sci-robot 123 published 2005 public