arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20643cs.LGcs.AI
收藏

TrajGPT-R: 基于强化学习增强的生成式预训练变换器生成城市移动轨迹

TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer

The University of Tokyo（东京大学）；Toyota Motor Corporation（丰田汽车公司）

Jiawei Wang, Chuang Yang, Jiawei Yong, Xiaohang Xu, Hongjun Wang, Noboru Koshizuka, Shintaro Fukushima, Ryosuke Shibasaki, Renhe Jiang

备注：
TrajGPT-R is a Reinforcement Learning-Enhanced Generative Pre-trained Transformer for Mobility Trajectory Generation
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

TrajGPT-R通过强化学习增强的生成式预训练变换器生成城市移动轨迹，提升了轨迹生成的可靠性和多样性，为交通管理和城市规划提供支持。

摘要：

移动轨迹对于理解城市动态和增强城市规划至关重要，但获取此类数据通常受到隐私问题的阻碍。本研究介绍了一种生成大规模城市移动轨迹的创新框架，采用了一种新的基于变换器模型的预训练和微调两阶段过程。最初，轨迹生成被概念化为一个离线强化学习（RL）问题，在标记化过程中实现了词汇空间的显著减少。逆强化学习（IRL）的整合使得能够捕捉轨迹级的奖励信号，利用历史数据推断个体移动偏好。随后，预训练模型通过构建的奖励模型进行微调，有效解决了传统基于RL的自回归方法中的长期信用分配和稀疏奖励环境处理问题。在多个数据集上的全面评估表明，我们的框架在可靠性和多样性方面明显优于现有模型。我们的发现不仅推进了城市移动建模领域，还提供了一种稳健的方法来模拟城市数据，对交通管理和城市发展规划具有重要意义。实现已公开在https://github.com/Wangjw6/TrajGPT_R。

英文摘要：

Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating large-scale urban mobility trajectories, employing a novel application of a transformer-based model pre-trained and fine-tuned through a two-phase process. Initially, trajectory generation is conceptualized as an offline reinforcement learning (RL) problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning (IRL) allows for the capture of trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences. Subsequently, the pre-trained model is fine-tuned using the constructed reward model, effectively addressing the challenges inherent in traditional RL-based autoregressive methods, such as long-term credit assignment and handling of sparse reward environments. Comprehensive evaluations on multiple datasets illustrate that our framework markedly surpasses existing models in terms of reliability and diversity. Our findings not only advance the field of urban mobility modeling but also provide a robust methodology for simulating urban data, with significant implications for traffic management and urban development planning. The implementation is publicly available at https://github.com/Wangjw6/TrajGPT_R.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑