Learning Improvement Heuristics for Solving Routing Problems
This addresses the problem of suboptimal routing solutions for logistics and operations research, offering a novel learning-based alternative to hand-crafted rules, though it builds incrementally on existing deep learning methods.
The paper tackles the gap between deep learning-based construction heuristics and optimal solutions in routing problems by proposing a deep reinforcement learning framework to learn improvement heuristics, achieving state-of-the-art performance on TSP and CVRP with generalization to different sizes and real-world data.
Recent studies in using deep learning to solve routing problems focus on construction heuristics, the solutions of which are still far from optimality. Improvement heuristics have great potential to narrow this gap by iteratively refining a solution. However, classic improvement heuristics are all guided by hand-crafted rules which may limit their performance. In this paper, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems. We design a self-attention based deep architecture as the policy network to guide the selection of next solution. We apply our method to two important routing problems, i.e. travelling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Experiments show that our method outperforms state-of-the-art deep learning based approaches. The learned policies are more effective than the traditional hand-crafted ones, and can be further enhanced by simple diversifying strategies. Moreover, the policies generalize well to different problem sizes, initial solutions and even real-world dataset.