Explainable Planner Selection

Ferber, Patrick and Seipp, Jendrik. (2020) Explainable Planner Selection. In Proceedings of the International Workshop of Explainable AI Planning (XAIP).

[img] PDF - Published Version

Official URL: https://edoc.unibas.ch/81249/

Downloads: Statistics Overview


Since no classical planner consistently outperforms all oth ers, it is important to select a planner that works well for a given classical planning task. The two strongest approaches for planner selection use image and graph convolutional neu ral networks. They have the drawback that the learned mod els are not interpretable. To obtain explainable models, we identify a small set of simple task features and show that el ementary and interpretable machine learning techniques can use these features to solve as many tasks as the approaches based on neural networks.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Ferber, Patrick and Seipp, Jendrik
Item Type:Other
Note:Publication type according to Uni Basel Research Database: Other publications
Related URLs:
edoc DOI:
Last Modified:02 Mar 2021 11:45
Deposited On:02 Mar 2021 11:45

Repository Staff Only: item control page