# Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior

arXiv: https://arxiv.org/abs/2505.00439 · HTML: https://mlsanity.com/paper/2505.00439/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 7 of 7)

- [ASNets: Deep Learning for Generalised Planning](https://mlsanity.com/paper/1908.01362/) (2019)
- [Learning Generalized Reactive Policies using Deep Neural Networks](https://mlsanity.com/paper/1708.07280/) (2017)
- [Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits](https://mlsanity.com/paper/2109.10129/) (2021)
- [Generalized Planning With Deep Reinforcement Learning](https://mlsanity.com/paper/2005.02305/) (2020)
- [Action Schema Networks: Generalised Policies with Deep Learning](https://mlsanity.com/paper/1709.04271/) (2017)
- [Learning Generalized Policies Without Supervision Using GNNs](https://mlsanity.com/paper/2205.06002/) (2022)
- [Size Independent Neural Transfer for RDDL Planning](https://mlsanity.com/paper/1902.03081/) (2019)

## Built on by (most cited first, 3 of 3)

- [Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study](https://mlsanity.com/paper/2508.18515/) (2025)
- [Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)](https://mlsanity.com/paper/2603.17544/) (2026)
- [Generating Instance Generators in PDDL Planning](https://mlsanity.com/paper/2609.06071/) (2026)

## Abstract (arXiv)

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.