EUVIMEDEUVIMED entdecken
Crossref

Learning General Policies for Planning through GPT Models

Nicholas Rossetti, Massimiliano Tummolo, Alfonso Emilio Gerevini, Luca Putelli, Ivan Serina, Mattia Chiari, Matteo Olivato

Proceedings of the International Conference on Automated Planning and Scheduling · 30.05.2024 · 34 · 500-508

DOI: 10.1609/icaps.v34i1.31510 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 30.05.2024. Verfasst von Nicholas Rossetti und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformer-based architectures, such as T5, BERT and GPT, have demonstrated revolutionary capabilities in Natural Language Processing. Several studies showed that deep learning models using these architectures not only possess remarkable linguistic knowledge, but they also exhibit forms of factual knowledge, common sense, and even programming skills. However, the scientific community still debates about their reasoning capabilities, which have been recently tested in the context of automated AI planning; the literature presents mixed results, and the prevailing view is that current transformer-based models may not be adequate for planning. In this paper, we address this challenge differently. We introduce a GPT-based model customised for planning (PLANGPT) to learn a general policy for classical planning by training the model from scratch with a dataset of solved planning instances. Once PLANGPT has been trained for a domain, it can be used to generate a solution plan for an input problem instance in that domain. Our training procedure exploits automated planning knowledge to enhance the performance of the trained model. We build and evaluate our GPT model with several planning domains, and we compare its performance w.r.t. other recent deep learning techniques for generalised planning, demonstrating the effectiveness of the proposed approach.

Zitieren

APA

Rossetti, N., Tummolo, M., Gerevini, A. E., Putelli, L., Serina, I., Chiari, M., & Olivato, M. (2024). Learning General Policies for Planning through GPT Models. Proceedings of the International Conference on Automated Planning and Scheduling, 34, 500-508. https://doi.org/10.1609/icaps.v34i1.31510

Vancouver

Rossetti N, Tummolo M, Gerevini AE, Putelli L, Serina I, Chiari M, et al. Learning General Policies for Planning through GPT Models. Proceedings of the International Conference on Automated Planning and Scheduling. 2024;34:500-508. doi:10.1609/icaps.v34i1.31510

BibTeX
@article{Rossetti2024,
  author = {Rossetti, Nicholas and Tummolo, Massimiliano and Gerevini, Alfonso Emilio and Putelli, Luca and Serina, Ivan and Chiari, Mattia and Olivato, Matteo},
  title = {Learning General Policies for Planning through GPT Models},
  journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
  year = {2024},
  volume = {34},
  pages = {500--508},
  doi = {10.1609/icaps.v34i1.31510}
}
Kostenlos starten →