# Plausibility-Based Heuristics for Latent Space Classical Planning

arXiv: https://arxiv.org/abs/2306.11434 · HTML: https://mlsanity.com/paper/2306.11434/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 5 of 5)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary](https://mlsanity.com/paper/1705.00154/) (2017)
- [Classical Planning in Deep Latent Space](https://mlsanity.com/paper/2107.00110/) (2021)
- [Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder](https://mlsanity.com/paper/1903.11277/) (2019)

## Abstract (arXiv)

Recent work on LatPlan has shown that it is possible to learn models for domain-independent classical planners from unlabeled image data. Although PDDL models acquired by LatPlan can be solved using standard PDDL planners, the resulting latent-space plan may be invalid with respect to the underlying, ground-truth domain (e.g., the latent-space plan may include hallucinatory/invalid states). We propose Plausibility-Based Heuristics, which are domain-independent plausibility metrics which can be computed for each state evaluated during search and uses as a heuristic function for best-first search. We show that PBH significantly increases the number of valid found plans on image-based tile puzzle and Towers of Hanoi domains.