Metraipolis › archive › dc_716a0645eb04

Multitask Reinforcement Learning for Assisting Choice Model Specification — arXiv:2609.18441

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18441
License (as archived)
CC0-1.0
Archived
2026-10-15T14:09:22.002Z
SHA-256 of the archived text
692faf6cc673723165ec3a5419b7a8eff759332f277e0ab4ad1c14c858316566
Stable URL of this page
https://metraipolis.com/documento/dc_716a0645eb04

How to cite

Multitask Reinforcement Learning for Assisting Choice Model Specification — arXiv:2609.18441 — arXiv (en), https://arxiv.org/abs/2609.18441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_716a0645eb04 (Metraipolis archive dc_716a0645eb04, sha256 692faf6cc673723165ec3a5419b7a8eff759332f277e0ab4ad1c14c858316566)
BibTeX
@misc{dc716a0645eb04,
  title = {Multitask Reinforcement Learning for Assisting Choice Model Specification — arXiv:2609.18441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_716a0645eb04; sha256 692faf6cc673723165ec3a5419b7a8eff759332f277e0ab4ad1c14c858316566},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and behavioural plausibility. We present Delphos, a multitask reinforcement learning framework that learns transferable specification strategies across transport choice datasets. Delphos frames model specification as a sequential decision-making problem in which it applies a sequence of modelling actions and receives feedback from an estimation environment based on model performance and convergence. To transfer modelling decisions across datasets with different sets of variables, Delphos represents utility specifications as sets of modelling terms using a DeepSet-Q architecture, allowing a shared specification policy to learn across multiple datasets. Trained on nine transport choice datasets, Delphos consistently outperforms independently trained single-task agents, indicating that sharing modelling experience improves learning efficiency and helps identify promising sequences of modelling decisions with fewer unsuccessful estimation attempts. When applied without further training to the unseen Swissmetro and Decisions datasets, the same agent identifies competitive specifications in less than 20 minutes on a standard CPU. It achieves a higher log-likelihood per observation than the VNS metaheuristic on Swissmetro and performance comparable to a published MNL specification developed by expert modellers on Decisions. These findings show that accumulating and reusing modelling experience enables Delphos to function as an intelligent assistant for discrete choice model specification. It reduces manual trial-and-error while allowing modellers to retain control over model diagnosis, refinement, and final selection.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-17 in econ.GN).
Categorie arXiv: General Economics (econ.GN) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.18441 — 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 2026-10-15T13:51:22.017Z dalla pagina https://arxiv.org/catchup/econ.GN/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).