SP
BravenNow
TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer
| USA | technology | ✓ Verified - arxiv.org

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

#TrajGPT-R #Urban Mobility Trajectory #Reinforcement Learning #Generative Pre-trained Transformer #Privacy Concerns #Urban Planning #Machine Learning #Data Generation

📌 Key Takeaways

  • Researchers developed TrajGPT-R framework for generating urban mobility trajectories
  • The technology uses reinforcement learning-enhanced generative pre-trained transformers
  • The framework addresses privacy concerns while enabling urban planning
  • The model outperforms existing approaches in reliability and diversity

📖 Full Retelling

Researchers led by Jiawei Wang and a team of eight collaborators introduced TrajGPT-R, a novel framework for generating urban mobility trajectories using reinforcement learning-enhanced generative pre-trained transformer technology, on the arXiv preprint server on February 24, 2026, addressing critical privacy concerns that have traditionally limited access to valuable urban mobility data essential for city planning and analysis. TrajGPT-R represents a significant advancement in urban mobility modeling by employing a two-phase process that pre-trains and fine-tunes a transformer-based model. The researchers conceptualized trajectory generation as an offline reinforcement learning problem, achieving substantial reduction in vocabulary space during tokenization. By integrating Inverse Reinforcement Learning, the framework effectively captures trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences while maintaining privacy. The innovative approach overcomes key challenges in traditional reinforcement learning-based autoregressive methods, particularly long-term credit assignment and handling sparse reward environments. According to the research team, comprehensive evaluations across multiple datasets demonstrate that TrajGPT-R significantly outperforms existing models in both reliability and diversity of generated trajectories.

🏷️ Themes

Urban Mobility, Machine Learning, Privacy Technology

📚 Related People & Topics

Urban planning

Urban planning

Technical process of land use and urban design

Urban planning (also called city planning or town planning in some contexts) is the process of developing and designing land use and the built environment, including air, water, and the infrastructure passing into and out of urban areas, such as transportation, communications, and distribution netwo...

View Profile → Wikipedia ↗
Reinforcement learning

Reinforcement learning

Field of machine learning

In machine learning and optimal control, reinforcement learning (RL) is concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal. Reinforcement learning is one of the three basic machine learning paradigms, alongside supervised learnin...

View Profile → Wikipedia ↗

Machine learning

Study of algorithms that improve automatically through experience

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Within a subdiscipline in machine learning, advances i...

View Profile → Wikipedia ↗

Entity Intersection Graph

Connections for Urban planning:

🌐 Smart city 1 shared
👤 New Yorker 1 shared
🌐 Fifty Shades Freed (film) 1 shared
🌐 Eric Adams 1 shared
🌐 East Harlem 1 shared
View full profile
Original Source
--> Computer Science > Machine Learning arXiv:2602.20643 [Submitted on 24 Feb 2026] Title: TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer Authors: Jiawei Wang , Chuang Yang , Jiawei Yong , Xiaohang Xu , Hongjun Wang , Noboru Koshizuka , Shintaro Fukushima , Ryosuke Shibasaki , Renhe Jiang View a PDF of the paper titled TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer, by Jiawei Wang and 8 other authors View PDF HTML 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 problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning 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 this https...
Read full article at source

Source

arxiv.org

More from USA

News from Other Countries

🇬🇧 United Kingdom

🇺🇦 Ukraine