Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Study

TL;DR

This study investigates how hyperparameters of Weisfeiler-Leman Features influence planning efficiency, demonstrating that optimal hyperparameters improve execution time and are consistent across domains, with minimal correlation between training and planning metrics.

Contribution

The paper introduces new hyperparameters for WLFs and provides a comprehensive analysis of their effects on planning performance using large sample sizes.

Findings

Optimal hyperparameters reduce execution time.

No significant correlation between training and planning metrics.

Robust hyperparameter set across multiple domains.

Abstract

Weisfeiler-Leman Features (WLFs) are a recently introduced classical machine learning tool for learning to plan and search. They have been shown to be both theoretically and empirically superior to existing deep learning approaches for learning value functions for search in symbolic planning. In this paper, we introduce new WLF hyperparameters and study their various tradeoffs and effects. We utilise the efficiency of WLFs and run planning experiments on single core CPUs with a sample size of 1,000,000 to understand the effect of hyperparameters on training and planning. Our experimental analysis show that there is a robust and best set of hyperparameters for WLFs across the tested planning domains. We find that the best WLF hyperparameters for learning heuristic functions minimise execution time rather than maximise model expressivity. We further statistically analyse and observe no significant correlation between training and planning metrics.