On Using Admissible Bounds for Learning Forward Search Heuristics

arXiv:2308.11905v3 Announce Type: replace-cross
Abstract: In recent years, there has been growing interest in utilizing modern machine learning techniques to learn heuristic functions for forward search algorithms. Despite this, there has been little theoretical understanding of what they should learn, how to train them, and why we do so. This lack of understanding has resulted in the adoption of diverse training targets (suboptimal vs optimal costs vs admissible heuristics) and loss functions (e.g., square vs absolute errors) in the literature. …

abstract algorithms arxiv cs.ai cs.lg functions heuristics learn machine machine learning machine learning techniques modern search search algorithms them train type understanding