Plausibility-Based Heuristics for Latent Space Classical Planning
Artificial Intelligence
2023-06-21 v1
Abstract
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.
Cite
@article{arxiv.2306.11434,
title = {Plausibility-Based Heuristics for Latent Space Classical Planning},
author = {Yuta Takata and Alex Fukunaga},
journal= {arXiv preprint arXiv:2306.11434},
year = {2023}
}