Plausibility-Based Heuristics for Latent Space Classical Planning
This addresses the issue of plan validity for researchers in AI planning, but is incremental as it builds on LatPlan.
The paper tackled the problem of latent-space plans being invalid in domain-independent classical planning from image data, and showed that Plausibility-Based Heuristics significantly increased the number of valid plans found in tile puzzle and Towers of Hanoi domains.
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.