Learning Improvement Heuristics for Solving Routing Problems

Wu, Yaoxin; Song, Wen; Cao, Zhiguang; Zhang, Jie; Lim, Andrew

doi:10.1109/tnnls.2021.3068828

Cited by 138 publications

(169 citation statements)

References 34 publications

Supporting

Mentioning

168

Contrasting

Order By: Relevance

“…Our results show that we can learn policies for the Euclidean TSP that achieve near-optimal solutions even when starting with poor quality solutions. Moreover, our approach can achieve better results than previous deep learning methods based on construction [5,7,18,20,24,29,38] and improvement [40] heuristics. Compared to [40], our method can be easily adapted to general k-opt and it is more sample efficient.…”

Section: Introductionmentioning

confidence: 85%

“…Recent works in machine learning and deep learning have focused on learning heuristics for combinatorial optimization problems [6,27]. For the TSP, both supervised learning [18,38] and reinforcement learning [5,7,20,24,40] methods have been proposed. The idea behind the proposed methods is that a machine learning method could learn better heuristics by extracting useful information directly from data, rather than having an explicitly programmed behavior.…”

Section: Introductionmentioning

confidence: 99%

“…Most approaches to the TSP have focused on learning construction heuristics, i.e., methods that can generate a solution sequentially by extending a partial tour. These methods employed sequence representations [5,38], graph neural networks [18,20] and attention mechanisms [7,24,40] resulting in high-quality solutions. Construction methods still require additional procedures such as beam search, classical improvement heuristics, and sampling to achieve such results.…”

Section: Introductionmentioning

confidence: 99%

“…Here, if we can learn a policy to improve a solution, we can use it to get better solutions from a construction heuristic or even random solutions. Recently, a deep reinforcement learning method [40] has been proposed for such a task, achieving near-optional results using node swap and 2-opt moves. However, the architecture has its output fixed by the number of possible moves, making it less favorable to expand to general k-opt, leading to lower optimality gaps [12].…”

Section: Introductionmentioning

confidence: 99%

“…Both problems have also been subject of the recent interest in combining machine learning and combinatorial optimization [8,16,19,34]. However, few previously proposed models can be seamlessly used in multiple routing problems [24,40].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning 2-Opt Heuristics for Routing Problems via Deep Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

Recent works using deep learning to solve routing problems such as the traveling salesman problem (TSP) have focused on learning construction heuristics. Such approaches find good quality solutions but require additional procedures such as beam search and sampling to improve solutions and achieve state-of-the-art performance. However, few studies have focused on improvement heuristics, where a given solution is improved until reaching a near-optimal one. In this work, we propose to learn a local search heuristic based on 2-opt operators via deep reinforcement learning. We propose a policy gradient algorithm to learn a stochastic policy that selects 2-opt operations given a current solution. Moreover, we introduce a policy neural network that leverages a pointing attention mechanism, which can be easily extended to more general k-opt moves. Our results show that the learned policies can improve even over random initial solutions and approach near-optimal solutions faster than previous state-of-the-art deep learning methods for the TSP. We also show we can adapt the proposed method to two extensions of the TSP: the multiple TSP and the Vehicle Routing Problem, achieving results on par with classical heuristics and learned methods.

show abstract

Section: Introductionmentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning 2-Opt Heuristics for Routing Problems via Deep Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

Modeling a novel heuristic model for handling vehicle routing using multiobjective optimization

Praveen¹,

Periasamy

Gurusamy³

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryElectric vehicles (EVs) are drastically growing, and their emergence is more popular. Moreover, with the constraint driving range, the batteries of these vehicles are rechargeable throughout the routes in various situations. Here, a new problem is formulated with the inclusion of both battery swapping and partial recharging decisions. The energy level and the routing directions are more important, and the investigators intend to handle these issues effectually. However, the major constraint is routing and time window. Here, a heuristic model (LTS‐RSS) is designed to find the best matching solution. A novel Random Sub‐Space (RSS) and local Tabu search (LTS) are modeled to handle these issues. The probabilistic model of RSS is anticipated by integrating the consequences of time windows and distances. The experimentation is done with an online database and used for performance validation. The outcomes show that the newly modeled (LTS‐RSS) approach enhances the significance of the model. The outcomes of all the instances with diverse strategies enhance the model's robustness and stability for resolving these issues. The empirical analysis is done with MATLAB 2020b simulator, and metrics like optimization of routing solution, the best vehicle, best distance, and numbers of vehicles are evaluated, and the outcomes are compared with various other approaches.

show abstract

Machine Learning for Combinatorial Optimization

Gasse

Lodi²

2022

Encyclopedia of Optimization

View full text Add to dashboard Cite

Learning Improvement Heuristics for Solving Routing Problems

Cited by 138 publications

References 34 publications

Learning 2-Opt Heuristics for Routing Problems via Deep Reinforcement Learning

Learning 2-Opt Heuristics for Routing Problems via Deep Reinforcement Learning

Modeling a novel heuristic model for handling vehicle routing using multiobjective optimization

Machine Learning for Combinatorial Optimization

Contact Info

Product

Resources

About