Abstract
The Trip Planning Query (TPQ), which returns the optimal path from the starting point to the destination that satisfies multiple types of points of interest (POIs) specified by the user, has attracted more and more attention. The most straightforward approach is to enumerate all the POI combinations that meet the user’s needs, and then select the path with the shortest distance. So this problem can be regarded as a combinatorial optimization problem and solved with deep reinforcement learning. Hence, in this paper, we explore the application of deep reinforcement learning in solving TPQ problem. Since the selection of POI can be considered as a sequence decision problem, we model it as a seq2seq problem. Firstly, to help the model reduce the difficulty of selection, we remove POIs that can not be the result, and propose a candidate set generation method. Its nodes are enough to meet the query POIs for the model to select different node sequences. Secondly, we use the encoder-decoder model base on attention mechanism. We concatenate the embedding of the start point, the end point and the selected nodes as the query part of the attention mechanism. We mask the same poi after select so that the model can solve the TPQ problem. Finally, we employ the REINFORCE method for training with a greedy baseline. Our model has a good performance on different maps, different POI densities, and different numbers of required POIs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, Y. Cheng, D., Marios, H., George, K., Teng, S.: On trip planning queries in spatial databases. In: SSTD, pp. 273–290 (2005)
Tanzima, H., Tahrima, H., Mohammed A., Lars, K.: Group trip planning queries in spatial databases. In: SSTD, pp. 259–276 (2013)
Mehdi, S., Mohammad, R., Kolahdouzan, C.S.: The optimal sequenced route query. VLDB J. 17(4), 765–787 (2008)
Ouyang, D., Qin, L., Chang, L., Lin, X., Zhang, Y., Zhu, Q.: When hierarchy meets 2-Hop-labeling: efficient shortest distance queries on road networks. In: SIGMOD, pp. 709–724 (2018)
Anasthasia, A., Md. Saiful, I., David, T., Muhammad, A.:IG-Tree: an efficient spatial keyword index for planning best path queries on road networks. In: WWW, vol. 22(4), pp. 1359–1399 (2019)
Nina, M., Sergei, S., Sergei, I. Evgeny, B.: Reinforcement learning for combinatorial optimization: A Survey. CoRR abs/ arXiv: 2003.03600 (2020)
Applegate, L., Bixby, E., Vaek, C., Cook, J.: The traveling salesman problem: a computational study. In: PUP (2006)
Hopfield, J.: Neural computation of decisions in optimization problems. Biol. Cybern. 52(1985)
Petar, V., Guillem, C., Arantxa, C., Adriana, R., Pietro, L., Yoshua B.: Graph attention networks. In: ICLR (Poster) (2018)
Iddo, D.A., et al.: Learning to solve combinatorial optimization problems on real-world graphs in linear time. In: ICMLA, pp. 19–24 (2020)
Oriol, V., Meire, F., Navdeep, J.: Pointer networks. In: NIPS, pp. 2692–2700 (2015)
Ashish, V., et al: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
Yoav, K., Lior, W.: Learning the Multiple Traveling Salesmen Problem with Permutation Invariant Pooling Networks. CoRR abs/ arXiv: 1803.09621 (2018)
Michel, D., Pierre, C., Alexandre, L., Yossiri, A., Louis-Martin, R.: Learning heuristics for the TSP by policy gradient. In: CPAIOR, pp. 170–181 (2018)
Wouter, K., Herke van, H., Max, W.: Attention, learn to solve routing problems! In: ICLR (Poster) (2019)
Xavier, B., Thomas, L.: The Transformer Network for the Traveling Salesman Problem. CoRR abs/ arXiv: 2103.03012 (2021)
Acknowledgements
The research work was partially supported by the Shenyang Young and Middle-aged Scientific and Technological Innovation Talent Support Plan under Grant No. RC220504; and the Natural Science Foundation of Liaoning Education Department under Grant No. LJKZ0205.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, C., Zhao, Y., Li, J., Guo, N., Zhu, R., Qiu, T. (2023). Deep Reinforcement Learning for Solving the Trip Planning Query. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14176. Springer, Cham. https://doi.org/10.1007/978-3-031-46661-8_38
Download citation
DOI: https://doi.org/10.1007/978-3-031-46661-8_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46660-1
Online ISBN: 978-3-031-46661-8
eBook Packages: Computer ScienceComputer Science (R0)