Abstract
The vehicle routing problem is a well known class of NP-hard combinatorial optimisation problems in literature. Traditional solution methods involve either carefully designed heuristics, or time-consuming metaheuristics. Recent work in reinforcement learning has been a promising alternative approach, but has found it difficult to compete with traditional methods in terms of solution quality. This paper proposes a hybrid approach that combines reinforcement learning, policy rollouts, and a satisfiability solver to enable a tunable tradeoff between computation times and solution quality. Results on a popular public data set show that the algorithm is able to produce solutions closer to optimal levels than existing learning based approaches, and with shorter computation times than meta-heuristics. The approach requires minimal design effort and is able to solve unseen problems of arbitrary scale without additional training. Furthermore, the methodology is generalisable to other combinatorial optimisation problems.
Abstract (translated)
URL
https://arxiv.org/abs/2206.06618
