# Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning

arXiv: https://arxiv.org/abs/2207.03336 · HTML: https://mlsanity.com/paper/2207.03336/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks](https://mlsanity.com/paper/1401.3839/) (2014)
- [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019)
- [Early Stopping is Nonparametric Variational Inference](https://mlsanity.com/paper/1504.01344/) (2015)
- [Patterns, predictions, and actions: A story about machine learning](https://mlsanity.com/paper/2102.05242/) (2021)
- [Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations](https://mlsanity.com/paper/1804.04577/) (2018)

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

- [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025)
- [Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planning](https://mlsanity.com/paper/2211.13316/) (2022)
- [Property-Guided LLM Program Synthesis for Planning](https://mlsanity.com/paper/2605.16142/) (2026)

## Abstract (arXiv)

We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems. RSL uses regression to select relevant sets of states at a range of different distances from the goal. RSL then formulates a Supervised Learning problem to obtain the parameters that define the NN heuristic, using the selected states labeled with exact or estimated distances to goal states. Our experimental study shows that RSL outperforms, in terms of coverage, previous classical planning NN heuristics functions while requiring two orders of magnitude less training time.