Machine Learning Assisted Evolutionary Computation for Vehicle Routing Problems

This competition aims to serve as a vehicle to bring together the latest developments of machine learning-assisted evolutionary computation for vehicle routing problems (VRPs). Results of current relevant research contain a lot of rich knowledge in evolutionary computation, which is however often discarded or not further investigated. These include different features of the problem/solutions to inform or drive the evolution/optimisation, different settings/operators/heuristics in effective evolutionary algorithms, and findings/evaluations of the search/fitness space. These can all be collected and processed as data, serving an excellent new problem domain for the machine learning community to enhance evolutionary computation.

VRP variants of different difficulties provide an ideal testbed to enable performance comparison of machine learning-assisted computational optimisation. Fostering, reusing, and interpreting the rich knowledge building ML4VRP remains a challenge for researchers across disciplines, however, is highly rewarding to further advance human-designed evolutionary computation.

In this competition, there are two tracks: CVRP (the most basic model) and CVRPTW (VRP with Capacity and Time Window constraints). Participants must develop machine learning model(s) which can design and enhance evolutionary computational algorithms or meta-heuristics for solving VRPs.

Participants must submit descriptions of the developed algorithms and the produced solutions for the corresponding CVRP/CVRPTW instances. Submissions will be evaluated on randomly selected instances from the benchmark CVRP/CVRPTW instances with an evaluator. The most widely adapted evaluation function, i.e. to minimise the number of vehicles and total travel distance, is used to determine the best machine learning assisted evolutionary algorithms for solving VRPs. The algorithms which produced the best average fitness for solving VRPs will receive the highest score.

Important: Instance and Solution Formats

In this competition, we follow the convention used by the recent DIMACS VRP challenge [9] for instance format and solution format. Specifically, solutions should be represented in the CVRPLIB format. 

We use the example solution below to explain the specifics of the instance and solution formats for the CVRP track and the CVRPTW track.

Route #1: 3 1 2

Route #2: 6 5 4

CVRP track

CVRP instances are given in the TSPLIB95 format [10], i.e., locations are numbered from 1 to n. Particularly, the depot is always in location 1, and customers are numbered from node 2 to node n. 

It is worth noting that due to historical reasons, the CVRPLIB solution format uses a convention that is slightly different from TSPLIB95, i.e., customers are numbered from 1 to n-1. Therefore, the given solution corresponds to routes 1-> 4 ->2 -> 3 -> 1 and 1 ->7 -> 6 -> 5 -> 1 in TSPLIB95 numbering.

Further explanations about the solution format can be found in the DIMACS CVRP challenge documentation. 

CVRPTW

CVRPTW instances are given in the widely accepted standard format for this specific variant. In CVRPTW instances, nodes are numbered from 0 to n. Node 0 is the depot, and customers are from node 1 to node n. 

The example solution corresponds to routes  0-> 3 ->1 -> 2 -> 0 and 0 ->6 -> 5 -> 4 -> 0. 

Participants could also submit a two-page abstract by 8 April 2024, to be included in the GECCO proceedings if accepted. Please refer to the Information for authors of "2-page Competition Abstracts" at https://gecco-2024.sigevo.org/Paper-Submission-Instructions.

Participants are also invited to submit a full paper to a special issue on ML4VRP in a journal. Details will be made available on the competition website as soon as the dates are agreed upon. We also encourage participants to attend GECCO 2024.

To break the ties where two or more algorithms achieve the same objective function value (with a precision of 3 decimal places) on a given instance, the points awarded to the corresponding ranking positions are added together and then distributed equally among the tied algorithms. This ensures that the total number of points awarded for each instance remains the same, and no algorithm is unfairly advantaged or disadvantaged with a tie.

The winner of the competition is the algorithm with the most points. In the case where two or more algorithms are awarded the same total points, the algorithm with more wins (the number of times it is ranked the first among all competing algorithms) is ranked first. If there is still a tie, the winner will go to the algorithm which is ranked the most second places, and so on.