<?xml version="1.0" encoding="utf-8" ?>
<entry xmlns="http://www.w3.org/2005/Atom" xmlns:sword="http://purl.org/net/sword/">
  <link rel="self" href="http://cogprints.org/cgi/export/eprint/4989/Atom/cogprints-eprint-4989.xml"/>
  <link rel="edit" href="http://cogprints.org/id/eprint/4989"/>
  <link rel="edit-media" href="http://cogprints.org/id/eprint/4989/contents"/>
  <link rel="contents" href="http://cogprints.org/id/eprint/4989/contents"/>
  <link rel="alternate" href="http://cogprints.org/id/eprint/4989"/>
  <published>2006-07-23Z</published>
  <updated>2011-03-11T08:56:31Z</updated>
  <id>http://cogprints.org/id/eprint/4989</id>
  <category term="confposter" label="Conference Poster" scheme="http://cogprints.org/data/eprint/type"/>
  <category term="archive" label="Live Archive" scheme="http://eprints.org/ep2/data/2.0/eprint/eprint_status"/>
  <link rel="http://purl.org/net/sword/terms/statement" href="http://cogprints.org/id/eprint/4989"/>
  <sword:state href="http://eprints.org/ep2/data/2.0/eprint/eprint_status/archive"/>
  <sword:stateDescription>This item is in the repository with the URL: http://cogprints.org/id/eprint/4989</sword:stateDescription>
  <sword:originalDeposit href="http://cogprints.org/id/eprint/4989">
    <sword:depositedOn>2006-07-23Z</sword:depositedOn>
  </sword:originalDeposit>
  <title type="xhtml">Speeding up Learning with Dynamic Environment
Shaping in Evolutionary Robotics</title>
  <summary type="xhtml">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.</summary>
  <author>
    <name>Nicolas Bredeche</name>
    <email/>
  </author>
  <author>
    <name>Louis Hugues</name>
    <email/>
  </author>
</entry>