Robustness in the long run: Auto-teaching vs Anticipation in Evolutionary Robotics - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Robustness in the long run: Auto-teaching vs Anticipation in Evolutionary Robotics

Abstract

In Evolutionary Robotics, auto-teaching networks, neural networks that modify their own weights during the life-time of the robot, have been shown to be powerful architectures to develop adaptive controllers. Unfortunately, when run for a longer period of time than that used during evolution, the long-term behavior of such networks can become unpredictable. This paper gives an example of such dangerous behavior, and proposes an alternative solution based on anticipation: as in auto-teaching networks, a secondary network is evolved, but its outputs try to predict the next state of the robot sensors. The weights of the action network are adjusted using some back-propagation procedure based on the errors made by the anticipatory network. First results -- in simulated environments -- show a tremendous increase in robustness of the long-term behavior of the controller.
Fichier principal
Vignette du fichier
ppsn2004.pdf (209.82 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00145172 , version 1 (09-05-2007)

Identifiers

  • HAL Id : inria-00145172 , version 1

Cite

Nicolas Godzik, Marc Schoenauer, Michèle Sebag. Robustness in the long run: Auto-teaching vs Anticipation in Evolutionary Robotics. Parallel Problem Solving from Nature, Sep 2004, Birmingham, pp.932-941. ⟨inria-00145172⟩
158 View
210 Download

Share

Gmail Facebook Twitter LinkedIn More