TY - JOUR
T1 - The First AI4TSP Competition
T2 - Learning to Solve Stochastic Routing Problems
AU - Bliek, Laurens
AU - da Costa, Paulo
AU - Refaei Afshar, Reza
AU - Zhang, Yingqian
AU - Catshoek, Tom
AU - Vos, Daniël
AU - Verwer, Sicco
AU - Schmitt-Ulms, Fynn
AU - Hottung, André
AU - Shah, Tapan
AU - Sellmann, Meinolf
AU - Tierney, Kevin
AU - Perreault-Lafleur, Carl
AU - Leboeuf, Caroline
AU - Bobbio, Federico
AU - Pepin, Justine
AU - Silva, Warley Almeida
AU - Gama, Ricardo
AU - Fernandes, Hugo L.
AU - Zaefferer, Martin
AU - López-Ibáñez, Manuel
AU - Irurozki, Ekhine
PY - 2022/1/25
Y1 - 2022/1/25
N2 - 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 a time-dependent orienteering problem with stochastic weights and time windows (TD-OPSWTW). It focused on two types of learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the setup of the competition, 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 AI methods.
AB - 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 a time-dependent orienteering problem with stochastic weights and time windows (TD-OPSWTW). It focused on two types of learning approaches: surrogate-based optimization and deep reinforcement learning. In this paper, we describe the problem, the setup of the competition, 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 AI methods.
KW - cs.AI
KW - 68T05
U2 - 10.48550/arXiv.2201.10453
DO - 10.48550/arXiv.2201.10453
M3 - Article
VL - 2022
JO - arXiv
JF - arXiv
M1 - 2201.10453
ER -