Open-Ended Evolutionary Robotics: an Information Theoretic Approach - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Open-Ended Evolutionary Robotics: an Information Theoretic Approach

Abstract

This paper is concerned with designing self-driven fitness functions for Embedded Evolutionary Robotics. The proposed approach considers the entropy of the sensori-motor stream generated by the robot controller. This entropy is computed using unsupervised learning; its maximization, achieved by an on-board evolutionary algorithm, implements a ``curiosity instinct'', favouring controllers visiting many diverse sensori-motor states (sms). Further, the set of sms discovered by an individual can be transmitted to its offspring, making a cultural evolution mode possible. Cumulative entropy (computed from ancestors and current individual visits to the sms) defines another self-driven fitness; its optimization implements a "discovery instinct'', as it favours controllers visiting new or rare sensori-motor states. Empirical results on the benchmark problems proposed by Lehman and Stanley (2008) comparatively demonstrate the merits of the approach.
Fichier principal
Vignette du fichier
paper204-PPSN2010.pdf (1.08 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00494237 , version 1 (24-06-2010)

Identifiers

  • HAL Id : inria-00494237 , version 1
  • ARXIV : 1006.4959

Cite

Pierre Delarboulas, Marc Schoenauer, Michèle Sebag. Open-Ended Evolutionary Robotics: an Information Theoretic Approach. PPSN XI, Sep 2010, Krakow, Poland. pp.334-343. ⟨inria-00494237⟩
154 View
225 Download

Altmetric

Share

Gmail Facebook X LinkedIn More