Deep Reinforcement Learning for Orienteering Problems Based on Decomposition
Abstract
This paper presents a new method for solving an orienteering problem (OP) by breaking it down into two parts: a knapsack problem (KP) and a traveling salesman problem (TSP). A KP solver is responsible for picking nodes, while a TSP solver is responsible for designing the proper path and assisting the KP solver in judging constraint violations. To address constraints, we propose a dual-population coevolutionary algorithm (DPCA) as the KP solver, which simultaneously maintains both feasible and infeasible populations. A dynamic pointer network (DYPN) is introduced as the TSP solver, which takes city locations as inputs and immediately outputs a permutation of nodes. The model, which is trained by reinforcement learning, can capture both the structural and dynamic patterns of the given problem. The model can generalize to other instances with different scales and distributions. Experimental results show that the proposed algorithm can outperform conventional approaches in terms of training, inference, and generalization ability.
Cite
@article{arxiv.2204.11575,
title = {Deep Reinforcement Learning for Orienteering Problems Based on Decomposition},
author = {Wei Liu and Tao Zhang and Rui Wang and Kaiwen Li and Wenhua Li and Kang Yang},
journal= {arXiv preprint arXiv:2204.11575},
year = {2023}
}
Comments
Since we have found that there are still several issues in this article. Some statements in the article are not rigorous, and the language and structure of the article still have a lot of room to polish. Moreover, the experiment of the article is not sufficient, and the experimental conclusion is not convincing enough. We sincerely hope to withdraw this article for further revision