arXiv cs.MA· Abdelkader Dib, Milos Balac·· 12 小时前AI 评分18
基于在线随机批量优化的智能体交通模型校准
Agent-Based Transport Model Calibration via Online Stochastic Batch Optimization
AI 导读
研究提出一种在线校准框架，将黑盒优化与机器学习中的随机批量优化结合，在单次仿真运行内完成参数估计，无需数百上千次独立仿真。以 MATSim 为例，把每次仿真迭代视为随机批次，使模型参数与智能体行为协同演化并收敛。在瑞士大规模交通场景中校准效用函数参数，模式分担率在典型仿真时长内与观测数据高度吻合。
正文 · 原文
Abstract:Calibrating agent-based models (ABMs) is computationally demanding, as traditional black-box optimization typically requires hundreds or thousands of independent simulation runs. To reduce this burden, we introduce an online calibration framework that estimates parameters within a single simulation run. The approach combines black-box optimization with stochastic batch optimization, a method widely applied in machine learning but not yet explored in ABM calibration. Using MATSim as a case study, we treat each simulation iteration as a stochastic batch, enabling incremental parameter updates as agents make decisions. This online calibration paradigm allows model parameters and agent behaviors to co-evolve, achieving convergence without restarting the simulation. We demonstrate the effectiveness of our method by calibrating utility function parameters in MATSim for a large-scale transportation scenario of Switzerland. Results show that mode shares align closely with observed data within a typical simulation timeframe, confirming the feasibility and efficiency of the approach. By embedding calibration directly into the simulation loop, our method opens new possibilities for real-time, scalable, and efficient calibration of complex ABMs.
| Comments: | Presented at the World Conference on Transport Research (WCTR 2026), Toulouse, France |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.32698 [cs.MA] |
| (or arXiv:2610.32698v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32698 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.3929/ethz-c-000799386
DOI(s) linking to related resources |
Submission history
From: Abdelkader Dib [view email]
[v1]
Fri, 23 Oct 2026 14:23:36 UTC (1,070 KB)
来源：arXiv cs.MA · arxiv.org