Minimize Surprise MAP-Elites: A Task-Independent MAP-Elites Variant for Swarms

Tanja Katharina Kaiser, Heiko Hamann

Abstract

Swarm robotics controllers are often automatically generated using methods of evolutionary computation with a task-specific fitness function to guide the optimization process. By contrast, our minimize surprise approach uses a task-independent fitness function to generate diverse behaviors over several independent evolutionary runs. Alternatives are divergent search algorithms rewarding behavioral novelty, such as novelty search, and quality-diversity algorithms generating diverse high-quality solutions, such as MAP-Elites. These approaches usually rely on task-dependent measures. We propose Minimize Surprise MAP-Elites, a task-independent MAP-Elites variant that combines MAP-Elites with our minimize surprise approach. Our first experiments result in high-quality solutions that lead to behavioral diversity across tasks and within tasks.

OriginalspracheDeutsch
TitelProceedings of the Genetic and Evolutionary Computation Conference Companion
ErscheinungsortNY, USA
Herausgeber (Verlag)Association for Computing Machinery
Erscheinungsdatum09.07.2022
ISBN (Print)978-1-4503-9268-6
DOIs
PublikationsstatusVeröffentlicht - 09.07.2022
VeranstaltungGECCO '22: Genetic and Evolutionary Computation Conference - Boston, USA / Vereinigte Staaten
Dauer: 09.07.202213.07.2022
https://gecco-2022.sigevo.org/HomePage

Zitieren