Quality Diversity Through Surprise
Autor: | Georgios N. Yannakakis, Antonios Liapis, Daniele Gravina |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer science media_common.quotation_subject 02 engineering and technology Machine learning computer.software_genre Theoretical Computer Science Search algorithm Robustness (computer science) Convergence (routing) 0202 electrical engineering electronic engineering information engineering Quality (business) Neural and Evolutionary Computing (cs.NE) Divergence (statistics) media_common business.industry Novelty Computer Science - Neural and Evolutionary Computing Surprise Computational Theory and Mathematics Task analysis 020201 artificial intelligence & image processing Artificial intelligence business computer Software |
Zdroj: | IEEE Transactions on Evolutionary Computation. 23:603-616 |
ISSN: | 1941-0026 1089-778X |
Popis: | Quality diversity is a recent family of evolutionary search algorithms which focus on finding several well-performing (quality) yet different (diversity) solutions with the aim to maintain an appropriate balance between divergence and convergence during search. While quality diversity has already delivered promising results in complex problems, the capacity of divergent search variants for quality diversity remains largely unexplored. Inspired by the notion of surprise as an effective driver of divergent search and its orthogonal nature to novelty this paper investigates the impact of the former to quality diversity performance. For that purpose we introduce three new quality diversity algorithms which employ surprise as a diversity measure, either on its own or combined with novelty, and compare their performance against novelty search with local competition, the state of the art quality diversity algorithm. The algorithms are tested in a robot navigation task across 60 highly deceptive mazes. Our findings suggest that allowing surprise and novelty to operate synergistically for divergence and in combination with local competition leads to quality diversity algorithms of significantly higher efficiency, speed and robustness. |
Databáze: | OpenAIRE |
Externí odkaz: |