# Learning Search-Space Specific Heuristics Using Neural Networks

arXiv: https://arxiv.org/abs/2306.04019 · HTML: https://mlsanity.com/paper/2306.04019/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 9 of 9)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019)
- [Learning Generalized Reactive Policies using Deep Neural Networks](https://mlsanity.com/paper/1708.07280/) (2017)
- [Learning to Rank for Synthesizing Planning Heuristics](https://mlsanity.com/paper/1608.01302/) (2016)
- [Size Independent Neural Transfer for RDDL Planning](https://mlsanity.com/paper/1902.03081/) (2019)
- [Transfer of Deep Reactive Policies for MDP Planning](https://mlsanity.com/paper/1810.11488/) (2018)
- [Towards learning domain-independent planning heuristics](https://mlsanity.com/paper/1707.06895/) (2017)
- [Scaling up Heuristic Planning with Relational Decision Trees](https://mlsanity.com/paper/1401.3885/) (2014)
- [Learning Classical Planning Strategies with Policy Gradient](https://mlsanity.com/paper/1810.09923/) (2018)

## Built on by (most cited first, 2 of 2)

- [On Using Admissible Bounds for Learning Forward Search Heuristics](https://mlsanity.com/paper/2308.11905/) (2023)
- [Learning Admissible Heuristics for A*: Theory and Practice](https://mlsanity.com/paper/2509.22626/) (2025)

## Abstract (arXiv)

We propose and evaluate a system which learns a neuralnetwork heuristic function for forward search-based, satisficing classical planning. Our system learns distance-to-goal estimators from scratch, given a single PDDL training instance. Training data is generated by backward regression search or by backward search from given or guessed goal states. In domains such as the 24-puzzle where all instances share the same search space, such heuristics can also be reused across all instances in the domain. We show that this relatively simple system can perform surprisingly well, sometimes competitive with well-known domain-independent heuristics.