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

Nicolas Godzik 1 Marc Schoenauer 1 Michèle Sebag 1
1 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00145172
Contributor : Marc Schoenauer <>
Submitted on : Wednesday, May 9, 2007 - 6:41:01 AM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on: Wednesday, April 7, 2010 - 3:33:14 AM

File

ppsn2004.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00145172, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

351

Files downloads

861