Publikation
Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
Timo P. Gros; Nicola Müller; Daniel Fiser; Isabel Valera; Verena Wolf; Jörg Hoffmann
In: The 35th International Conference on Automated Planning and Scheduling. International Conference on Automated Planning and Scheduling (ICAPS-2025), November 9-14, Melbourne, Australia, AAAI Press, 2025.
Zusammenfassung
Recent work has shown that successful per-domain generalizing action policies can be learned. Scaling behavior, from
small training instances to large test instances, is the key objective; and the use of validation instances larger than training
instances is one key to achieve it. Prior work has used fixed
validation sets. Here, we introduce a method generating the
validation set dynamically, on the fly, increasing instance size
so long as informative and feasible. We also introduce refined
methodology for evaluating scaling behavior, generating test
instances systematically to guarantee a given confidence in
coverage performance for each instance size. In experiments,
dynamic validation improves scaling behavior of GNN policies in all 9 domains used.