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.
Originalsprache | Deutsch |
---|---|
Titel | Proceedings of the Genetic and Evolutionary Computation Conference Companion |
Erscheinungsort | NY, USA |
Herausgeber (Verlag) | Association for Computing Machinery |
Erscheinungsdatum | 09.07.2022 |
ISBN (Print) | 978-1-4503-9268-6 |
DOIs | |
Publikationsstatus | Veröffentlicht - 09.07.2022 |
Veranstaltung | GECCO '22: Genetic and Evolutionary Computation Conference - Boston, USA / Vereinigte Staaten Dauer: 09.07.2022 → 13.07.2022 https://gecco-2022.sigevo.org/HomePage |