Dynamically generating larger validation instances during training selects planning policies that generalize to larger instances better than fixed validation sets, across all 9 domains tested.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior
Dynamically generating larger validation instances during training selects planning policies that generalize to larger instances better than fixed validation sets, across all 9 domains tested.