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

2026-02-24

AI Summary

This study addresses the challenge of limited access to real-world urban mobility trajectories due to privacy constraints, which hinders dynamic urban modeling and planning. The authors formulate trajectory generation as an offline reinforcement learning problem and propose a two-stage approach: first, they employ inverse reinforcement learning (IRL) to infer individual movement preferences from historical data by learning a reward function; then, they fine-tune a pre-trained generative Transformer using this reward function to enhance the long-term consistency and diversity of synthetic trajectories. Innovatively integrating IRL with a pre-trained Transformer—alongside trajectory tokenization and vocabulary compression techniques—the method effectively mitigates sparse rewards and long-horizon credit assignment issues. Evaluated on multiple real-world datasets, the approach significantly outperforms existing models in both realism and diversity of generated trajectories, offering high-quality synthetic data for traffic simulation and urban planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• urban mobility trajectory
• privacy
• trajectory generation
• urban planning
• data simulation

Innovation

• Reinforcement Learning
• Generative Pre-trained Transformer
• Inverse Reinforcement Learning
• Urban Mobility Trajectory
• Offline RL