Abstract
Reinforcement learning (RL) has seen increasing success at solving a variety of combinatorial optimization problems. These techniques have generally been applied to deterministic optimization problems with few side constraints, such as the traveling salesperson problem (TSP) or capacitated vehicle routing problem (CVRP). With this in mind, the recent IJCAI AI for TSP competition challenged participants to apply RL to a difficult routing problem involving optimization under uncertainty and time windows. We present the winning submission to the challenge, which uses the policy optimization with multiple optima (POMO) approach combined with efficient active search and Monte Carlo roll-outs. We present experimental results showing that our proposed approach outperforms the second place approach by 1.7%. Furthermore, our computational results suggest that solving more realistic routing problems may not be as difficult as previously thought.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We note that the TDOP is abbreviated as the TD-OPSWTW in some works.
- 2.
Although not the focus of our research, our approach can also generate complete solutions using the expected travel time for the supervised learning track, and these tie the winning team’s solutions and generate them in less computation time.
- 3.
We assume the penalty is large enough (\(p > r_i\)) such that, in the version of the problem with recourse, we should always avoid the late arrival penalty at nodes.
References
Basso, R., Kulcsár, B., Sanchez-Diaz, I., Qu, X.: Dynamic stochastic electric vehicle routing with safe reinforcement learning. Transp. Res. Part E: Logistics Transp. Rev. 157, 102496 (2022)
Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural Combinatorial Optimization with Reinforcement Learning. arXiv:1611.0 (2016)
Bengio, Y., Lodi, A., Prouvost, A.: Machine learning for combinatorial optimization: a methodological tour d’horizon. Eur. J. Oper. Res. 290, 405–421 (2020)
Bliek, L., et al.: The first AI4TSP competition: learning to solve stochastic routing problems (2022). https://doi.org/10.48550/arXiv.2201.10453
Bono, G.: Deep multi-agent reinforcement learning for dynamic and stochastic vehicle routing problems. Ph.D. thesis, Université de Lyon (2020)
Chen, X., Tian, Y.: Learning to perform local rewriting for combinatorial optimization. In: Advances in Neural Information Processing Systems, pp. 6278–6289 (2019)
Choo, J., et al.: Simulation-guided beam search for neural combinatorial optimization (2022). https://doi.org/10.48550/arXiv.2207.06190
de O. da Costa, P.R., Rhuggenaath, J., Zhang, Y., Akcay, A.: Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning. In: Asian Conference on Machine Learning, pp. 465–480. PMLR (2020)
Helsgaun, K.: An effective implementation of the Lin-Kernighan traveling salesman heuristic. Eur. J. Oper. Res. 126, 106–130 (2000)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. U.S.A. 79(8), 2554–2558 (1982)
Hottung, A., Bhandari, B., Tierney, K.: Learning a latent search space for routing problems using variational autoencoders. In: International Conference on Learning Representations (2021)
Hottung, A., Kwon, Y.D., Tierney, K.: Efficient active search for combinatorial optimization problems. In: International Conference on Learning Representations (2022)
Hottung, A., Tierney, K.: Neural large neighborhood search for the capacitated vehicle routing problem. In: European Conference on Artificial Intelligence, pp. 443–450 (2020)
Joe, W., Lau, H.C.: Deep reinforcement learning approach to solve dynamic vehicle routing problem with stochastic customers. Proc. Int. Conf. Autom. Plann. Sched. 30, 394–402 (2020)
Joshi, C.K., Cappart, Q., Rousseau, L.M., Laurent, T.: Learning TSP requires rethinking generalization. In: Michel, L.D. (ed.) 27th International Conference on Principles and Practice of Constraint Programming (CP 2021). Leibniz International Proceedings in Informatics (LIPIcs), vol. 210, pp. 33:1–33:21. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, Dagstuhl, Germany (2021)
Joshi, C.K., Laurent, T., Bresson, X.: An efficient graph convolutional network technique for the travelling salesman problem. arXiv:1906.01227 (2019)
Kool, W., van Hoof, H., Gromicho, J., Welling, M.: Deep policy dynamic programming for vehicle routing problems. In: International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pp. 190–213 (2022)
Kool, W., van Hoof, H., Welling, M.: Attention, learn to solve routing problems! International Conference on Learning Representations (2019). https://doi.org/10.48550/arXiv.1803.08475
Kwon, Y.D., Choo, J., Kim, B., Yoon, I., Gwon, Y., Min, S.: POMO: policy optimization with multiple optima for reinforcement learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol. 33, pp. 21188–21198. Curran Associates, Inc. (2020)
Li, S., Yan, Z., Wu, C.: Learning to delegate for large-scale vehicle routing. In: Advances in Neural Information Processing Systems. 34 (2021)
Sultana, N.N., Baniwal, V., Basumatary, A., Mittal, P., Ghosh, S., Khadilkar, H.: Fast approximate solutions using reinforcement learning for dynamic capacitated vehicle routing with time windows. arXiv preprint arXiv:2102.12088 (2021)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol. 30. Curran Associates, Inc. (2017)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. Adv. Neural Inf. Process. Syst. 28, 2692–2700 (2015)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Williams, R.J., Peng, J.: Function optimization using connectionist reinforcement learning algorithms. Connection Sci. 3(3), 241–268 (1991)
Wu, Y., Song, W., Cao, Z., Zhang, J., Lim, A.: Learning improvement heuristics for solving routing problems. IEEE Trans. Neural Netw. Learn. Syst. 33(9), 5057–5069 (2021)
Xin, L., Song, W., Cao, Z., Zhang, J.: NeuroLKH: combining deep learning model with lin-kernighan-helsgaun heuristic for solving the traveling salesman problem. In: Advances in Neural Information Processing Systems. 34 (2021)
Acknowledgments
Fynn Schmitt-Ulms was supported by the German Academic Exchange Service Research Internships in Science and Engineering (DAAD RISE) program. The computational experiments in this work have been performed using the Bielefeld GPU cluster. We thank the Bielefeld HPC.NRW team for their support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Schmitt-Ulms, F., Hottung, A., Sellmann, M., Tierney, K. (2022). Learning to Solve a Stochastic Orienteering Problem with Time Windows. In: Simos, D.E., Rasskazova, V.A., Archetti, F., Kotsireas, I.S., Pardalos, P.M. (eds) Learning and Intelligent Optimization. LION 2022. Lecture Notes in Computer Science, vol 13621. Springer, Cham. https://doi.org/10.1007/978-3-031-24866-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-24866-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24865-8
Online ISBN: 978-3-031-24866-5
eBook Packages: Computer ScienceComputer Science (R0)