دورية أكاديمية

The first AI4TSP competition: Learning to solve stochastic routing problems

التفاصيل البيبلوغرافية
العنوان: The first AI4TSP competition: Learning to solve stochastic routing problems
المؤلفون: Zhang, Yingqian, Bliek, Laurens, da Costa, Paulo, Afshar, Reza Refaei, Reijnen, Robbert, Catshoek, Tom, Vos, Daniel, Verwer, Sicco, Schmitt-Ulms, Fynn, Hottung, André, Shah, Tapan, Sellmann, Meinolf, Tierney, Kevin, Perreault-Lafleur, Carl, Leboeuf, Caroline, Bobbio, Federico, Pepin, Justine, Silva, Warley Almeida, Gama, Ricardo, Fernandes, Hugo L., Zaefferer, Martin, Lopez-Ibanez, Manuel, Irurozki, Ekhine
بيانات النشر: Elsevier
سنة النشر: 2023
المجموعة: PUB - Publications at Bielefeld University
مصطلحات موضوعية: AI for TSP competition, Travelling salesman problem, Routing problem, Stochastic combinatorial optimization, Surrogate-based optimization, Deep reinforcement learning
الوصف: Zhang Y, Bliek L, da Costa P, et al. The first AI4TSP competition: Learning to solve stochastic routing problems. Artificial Intelligence . 2023;319: 103918. ; This paper reports on the first international competition on AI for the traveling salesman problem (TSP) at the International Joint Conference on Artificial Intelligence 2021 (IJCAI-21). The TSP is one of the classical combinatorial optimization problems, with many variants inspired by real-world applications. This first competition asked the participants to develop algorithms to solve an orienteering problem with stochastic weights and time windows (OPSWTW). It focused on two learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the competition setup, and the winning methods, and give an overview of the results. The winning methods described in this work have advanced the state-of-the-art in using AI for stochastic routing problems. Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers. The simulator of the problem has been made open-source and can be used by other researchers as a benchmark for new
نوع الوثيقة: article in journal/newspaper
اللغة: English
العلاقة: info:eu-repo/semantics/altIdentifier/issn/0004-3702; info:eu-repo/semantics/altIdentifier/issn/1872-7921; info:eu-repo/semantics/altIdentifier/wos/000982510500001; https://pub.uni-bielefeld.de/record/2979705Test
الإتاحة: https://doi.org/10.1016/j.artint.2023.103918Test
https://pub.uni-bielefeld.de/record/2979705Test
حقوق: info:eu-repo/semantics/closedAccess
رقم الانضمام: edsbas.FA4F094E
قاعدة البيانات: BASE