Research on Construction Schedule Optimization Based on Q-Learning Algorithm

DOI

10.2991/978-94-6239-758-3_14How to use a DOI?

Keywords

Construction schedule; Q-Learning; Resource optimization; Dynamic scheduling

Abstract

Traditional schedule management methods such as the Critical Path Method (CPM) and Program Evaluation and Review Technique (PERT) have inherent limitations in dynamic construction environments due to their static planning nature and poor adaptability to uncertainties. This paper proposes a schedule optimization model based on the Q-Learning algorithm, which achieves dynamic resource allocation decisions through the construction of a state space, action space, and reward mechanism. Taking a large-scale commercial complex construction project as a case study, the experimental results demonstrate that compared with the traditional CPM method, the Q-Learning model reduces the total project duration by 15.3%, improves resource utilization by 22.1%, and effectively mitigates schedule delay risks. Under random disturbance scenarios including weather impacts and material shortages, the model exhibits strong robustness, with schedule recovery time reduced by 40% compared to manual adjustment. This research provides an intelligent scheduling tool for construction enterprises, promoting the transformation from static planning to dynamic optimization in schedule management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yang Xu
PY  - 2026
DA  - 2026/09/08
TI  - Research on Construction Schedule Optimization Based on Q-Learning Algorithm
BT  - Proceedings of the 2026 7th International Conference on Management Science and Engineering Management (ICMSEM 2026)
PB  - Atlantis Press
SP  - 147
EP  - 153
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-758-3_14
DO  - 10.2991/978-94-6239-758-3_14
ID  - Xu2026
ER  -