Towards Utilitarian Combinatorial Assignment with Deep Neural Networks and Heuristic Algorithms

This paper presents preliminary work on using deep neural networks to guide general-purpose heuristic algorithms for performing utilitarian combinatorial assignment. In more detail, we use learning in an attempt produce heuristics that can be used together with e.g., search generate feasible solutions of higher quality quickly. Our results indicate our approach could a promising future method constructing such heuristics.