Saved in:
Bibliographic Details
Main Authors: Gros, Timo P., Müller, Nicola J., Fiser, Daniel, Valera, Isabel, Wolf, Verena, Hoffmann, Jörg
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.00439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918005994160128
author Gros, Timo P.
Müller, Nicola J.
Fiser, Daniel
Valera, Isabel
Wolf, Verena
Hoffmann, Jörg
author_facet Gros, Timo P.
Müller, Nicola J.
Fiser, Daniel
Valera, Isabel
Wolf, Verena
Hoffmann, Jörg
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00439
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
Gros, Timo P.
Müller, Nicola J.
Fiser, Daniel
Valera, Isabel
Wolf, Verena
Hoffmann, Jörg
Machine Learning
Artificial Intelligence
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.
title Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.00439