Online Planner Selection with Graph Neural Networks and Adaptive Scheduling

Ma, Tengfei and Ferber, Patrick and Huo, Siyu and Chen, Jie and Katz, Michael. (2020) Online Planner Selection with Graph Neural Networks and Adaptive Scheduling. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), 34. pp. 5077-5084.

[img] PDF - Accepted Version

Official URL: https://edoc.unibas.ch/78713/

Downloads: Statistics Overview


Automated planning is one of the foundational areas of AI. Since no single planner can work well for all tasks and do- mains, portfolio-based techniques have become increasingly popular in recent years. In particular, deep learning emerges as a promising methodology for online planner selection. Owing to the recent development of structural graph repre- sentations of planning tasks, we propose a graph neural net- work (GNN) approach to selecting candidate planners. GNNs are advantageous over a straightforward alternative, the con- volutional neural networks, in that they are invariant to node permutations and that they incorporate node labels for better inference. Additionally, for cost-optimal planning, we propose a two- stage adaptive scheduling method to further improve the like- lihood that a given task is solved in time. The scheduler may switch at halftime to a different planner, conditioned on the observed performance of the first one. Experimental results validate the effectiveness of the proposed method against strong baselines, both deep learning and non-deep learning based. The code is available at https://github.com/matenure/GNN planner.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Ferber, Patrick
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:AAAI Press
Series Name:4
Note:Publication type according to Uni Basel Research Database: Conference paper
Related URLs:
Identification Number:
edoc DOI:
Last Modified:02 Oct 2020 12:32
Deposited On:02 Oct 2020 12:27

Repository Staff Only: item control page