A multi-agent reinforcement learning algorithm for spatial crowdsourcing task assignments considering workers’ path

被引：0

作者：

Ji M.-M. ^{[1
]}

Wu Z.-B. ^{[1
]}

机构：

[1] Business School, Sichuan University, Chengdu

来源：

Kongzhi yu Juece/Control and Decision | 2024年 / 39卷 / 01期

关键词：

multi-agent; path planning; reinforcement learning; road network; spatial crowdsourcing; task assignment;

D O I：

10.13195/j.kzyjc.2022.1319

中图分类号：

学科分类号：

摘要：

Matching tasks and workers is one of the core problems in spatial crowdsourcing research, but the impact of path planning of workers on task allocation results is usually ignored in the existing literature. There are problems with traditional task assignment methods including slow computing speed, small application scope, and unremarkable collaboration effect. From the perspective of a spatial crowdsourcing platform, this research is oriented toward the spatial crowdsourcing task assignment problem on the road networks and puts forward a QMIX-A* algorithm based on multiagent reinforcement learning considering workers’ path planning. The proposed approach with the minimum completion time of tasks as the objective can shorten the tasks’ average completion time, thereby improving users’ satisfaction. The effectiveness and stability of the QMIX-A* are verified by a large number of simulation studies. The results of the research can provide decision support for the task allocation and path optimization strategy selection of spatial crowdsourcing service platforms. © 2024 Northeast University. All rights reserved.

引用

页码：319 / 326

页数：7

共 24 条

[1]

Tong Y X, Zhou Z M, Zeng Y X, Et al., Spatial crowdsourcing: A survey, The VLDB Journal, 29, 1, pp. 217-250, (2020)

[2]

Pan Q X, Yin Z X, Dong H B, Et al., Spatiotemporal crowdsourcing task assignment algorithm based on tabu search, CAAI Transactions on Intelligent Systems, 15, 6, pp. 1040-1048, (2020)

[3]

Dai T, Shen J., A research on take-away delivery task selection in crowdsourcing, Industrial Engineering Journal, 24, 2, pp. 125-133, (2021)

[4]

Yu HY, Jiang RL., Studyonthereal-timeorderallocation and routing problem of takeout food distribution on crowdsourcing platform, Industrial Engineering and Management, 27, 2, pp. 146-152, (2022)

[5]

To H, Shahabi C, Kazemi L., A server-assigned spatial crowdsourcing framework, ACM Transactions on Spatial Algorithms and Systems, 1, 1, pp. 1-28, (2015)

[6]

Deng D X, Shahabi C, Demiryurek U., Maximizing the number of worker’s self-selected tasks in spatial crowdsourcing, Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 324-333, (2013)

[7]

Zhao Y, Ni Z W, Zhu X H, Et al., Multi-worker and multi-task path planning based on improved lion evolutionary algorithm for spatial crowdsourcing platform, Computer Science, 48, pp. 30-38, (2021)

[8]

Wu T Y, Chen J J, Jian J, Et al., The online pick-up and delivery vehicle routing problem under O2O delivery, Systems Engineering — Theory & Practice, 38, 11, pp. 2885-2891, (2018)

[9]

Safran M, Che D R., Efficient learning-based recommendation algorithms for top-N tasks and top-N workers in large-scale crowdsourcing systems, ACM Transactions on Information Systems, 37, 1, pp. 1-46, (2019)

[10]

Huang X H, Zhang X, Yang K M, Et al., Reinforcement learning online car-hailing order dispatch based on joint Q-value decomposition, Computer Engineering, 48, 12, pp. 296-303, (2022)

← 1 2 3 →