AINeutralarXiv – CS AI · 8h ago6/10
🧠
Learning Empirically Admissible Neural Heuristics for Combinatorial Search
Researchers introduce a framework for training neural networks to solve combinatorial puzzles optimally by enforcing admissibility constraints—ensuring heuristics never overestimate remaining costs. The method combines an underestimating Bellman operator with asymmetric loss functions and post-hoc calibration, achieving significant reductions in search node expansions while maintaining solution optimality.