Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal

Leah A. Chrestien, Tom'as Pevn'y, Stefan Edelkamp, Antonín Komenda
2/12/2026

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

In imitation learning for planning, parameters of heuristic functions are optimized against a set of solved problem instances. This work revisits the necessary and sufficient conditions of strictly optimally efficient heuristics for forward search algorithms, mainly A* and greedy best-first search, which expand only states on the returned optimal path. It then proposes a family of loss functions based on ranking tailored for a given variant of the forward search algorithm. Furthermore, from a learning theory point of view, it discusses why optimizing cost-to-goal \hstar\ is unnecessarily difficult. The experimental comparison on a diverse set of problems unequivocally supports the derived theory.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

81% match2025

Imitating Cost-Constrained Behaviors in Reinforcement Learning

80% match1 repo42024

A Generalization Result for Convergence in Learning-to-Optimize

80% match2026

Decision-Focused Learning to Predict Action Costs for Planning

79% match1 repo32024

SLOPE: Search with Learned Optimal Pruning-based Expansion

78% match1 repo22024

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching

78% match2023

Cite this paper

@article{chrestien2026optimize,
  title  = {Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal},
  author = {Leah A. Chrestien and Tom'as Pevn'y and Stefan Edelkamp and Antonín Komenda},
  year   = {2026},
  eprint = {2310.19463},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2310.19463},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.19463.svg)](https://codeofpaper.com/paper/2310.19463)

Discussion