Skip to Main content Skip to Navigation
Conference papers

Learning behaviour-performance maps with meta-evolution

David Bossens 1 Jean-Baptiste Mouret 2 Danesh Tarapore 1
2 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
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.
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/hal-02555231
Contributor : Jean-Baptiste Mouret <>
Submitted on : Monday, April 27, 2020 - 10:44:17 AM
Last modification on : Monday, June 22, 2020 - 5:01:22 PM

File

pap349s3-file1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02555231, version 1

Citation

David 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⟩

Share

Metrics

Record views

316

Files downloads

722