Representative Answer Sets: Collecting Something of Everything
Elisa Böhl, Sarah Alice Gaggl, Dominik Rusovac · Frontiers in artificial intelligence and applications · 2023
Answer set programming (ASP) is a popular problem solving paradigm with applications in planning and configuration. In practice, the number of answer sets can be overwhelmingly high, which naturally causes interest in a concise characterisation of the solution space in terms of representative answer sets. We establish a notion of representativeness that refers to the entropy of specified target atoms within a collection of answer sets. Accordingly, we propose different approaches for collecting such representative answer sets, based on answer set navigation. Finally, we conduct experiments using our prototypical implementation, which reveals promising results.