Learning behaviour-performance maps with meta-evolution - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Learning behaviour-performance maps with meta-evolution

Abstract

The MAP-Elites quality-diversity algorithm has been successful in robotics because it can create a behaviorally diverse set of solutions that later can be used for adaptation, for instance to unanticipated damages. In MAP-Elites, the choice of the behaviour space is essential for adaptation, the recovery of performance in unseen environments , since it defines the diversity of the solutions. Current practice is to hand-code a set of behavioural features, however, given the large space of possible behaviour-performance maps, the designer does not know a priori which behavioural features maximise a map's adaptation potential. We introduce a new meta-evolution algorithm that discovers those behavioural features that maximise future adaptations. The proposed method applies Covari-ance Matrix Adaptation Evolution Strategy to evolve a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. The method stores solutions found by MAP-Elites in a database which allows to rapidly construct new behaviour-performance maps on-the-fly. To evaluate this system , we study the gait of the RHex robot as it adapts to a range of damages sustained on its legs. When compared to MAP-Elites with user-defined behaviour spaces, we demonstrate that the meta-evolution system learns high-performing gaits with or without damages injected to the robot.
Fichier principal
Vignette du fichier
pap349s3-file1.pdf (3.78 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02555231 , version 1 (27-04-2020)

Identifiers

  • HAL Id : hal-02555231 , version 1

Cite

David M Bossens, Jean-Baptiste Mouret, Danesh Tarapore. Learning behaviour-performance maps with meta-evolution. GECCO'20 - Genetic and Evolutionary Computation Conference, Jul 2020, Cancun, Mexico. ⟨hal-02555231⟩
349 View
482 Download

Share

Gmail Mastodon Facebook X LinkedIn More