Learning the Multiple Traveling Salesmen Problem with Permutation Invariant Pooling Networks
While there are optimal TSP solvers as well as recent learning-based approaches, the generalization of the TSP to the multiple Traveling Salesmen Problem is much less studied. Here, we design a neural network solution that treats the salesmen, the cities, and the depot as three different sets of varying cardinalities. Coupled with a normalization algorithm, a dedicated loss, and a search method, our solution is shown in two benchmarks to outperform all the meta-heuristics of the leading solver in the field.
READ FULL TEXT