Metraipolis › archive › dc_c2b9c8ada383

Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation Guidance — arXiv:2608.30317

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30317
License (as archived)
CC0-1.0
Archived
2026-10-17T07:52:35.458Z
SHA-256 of the archived text
f25030c1d91c9c893cbdca7779c2612907e6a01878a6b072dd34d02e09eaa5f8
Stable URL of this page
https://metraipolis.com/documento/dc_c2b9c8ada383

How to cite

Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation Guidance — arXiv:2608.30317 — arXiv (en), https://arxiv.org/abs/2608.30317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2b9c8ada383 (Metraipolis archive dc_c2b9c8ada383, sha256 f25030c1d91c9c893cbdca7779c2612907e6a01878a6b072dd34d02e09eaa5f8)
BibTeX
@misc{dcc2b9c8ada383,
  title = {Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning with Link-Flow Propagation Guidance — arXiv:2608.30317},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30317},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2b9c8ada383; sha256 f25030c1d91c9c893cbdca7779c2612907e6a01878a6b072dd34d02e09eaa5f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dynamic origin-destination (OD) matrix estimation calibrates time-dependent input demand for simulations to reproduce observed link flows. Reinforcement learning is well suited to online estimation because a trained policy estimates demand in a single evaluation, but varying target flows complicate learning from aggregate rewards. We propose reinforcement learning with link-flow propagation guidance (LFPG-RL), combining simulated vehicle propagation records with downstream errors to guide individual OD components. Using 250 weekday link-flow trajectories from a Melbourne arterial network, LFPG-RL achieves a mean test root mean squared error (RMSE) of 7.41 vehicles per 15-minute interval, mean absolute percentage error of 31.24%, and Pearson correlation of 0.987. Comparisons with optimisation, filtering and reinforcement learning without guidance show a 40.1% RMSE reduction over the strongest baseline, gradient descent with propagation guidance. LFPG-RL enables rapid demand updates that keep traffic simulations consistent with observed conditions, supporting the evaluation of traffic management strategies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30317 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.854Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).