Graph Learning for Planning: The Story Thus Far and Open Challenges
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909413238898688 |
|---|---|
| author | Chen, Dillon Z. Hao, Mingyu Thiébaux, Sylvie Trevizan, Felipe |
| author_facet | Chen, Dillon Z. Hao, Mingyu Thiébaux, Sylvie Trevizan, Felipe |
| contents | Graph learning is naturally well suited for use in planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. In this paper, we study the usage of graph learning for planning thus far by studying the theoretical and empirical effects on learning and planning performance of (1) graph representations of planning tasks, (2) graph learning architectures, and (3) optimisation formulations for learning. Our studies accumulate in the GOOSE framework which learns domain knowledge from small planning tasks in order to scale up to much larger planning tasks. In this paper, we also highlight and propose the 5 open challenges in the general Learning for Planning field that we believe need to be addressed for advancing the state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02136 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Graph Learning for Planning: The Story Thus Far and Open Challenges Chen, Dillon Z. Hao, Mingyu Thiébaux, Sylvie Trevizan, Felipe Artificial Intelligence Graph learning is naturally well suited for use in planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. In this paper, we study the usage of graph learning for planning thus far by studying the theoretical and empirical effects on learning and planning performance of (1) graph representations of planning tasks, (2) graph learning architectures, and (3) optimisation formulations for learning. Our studies accumulate in the GOOSE framework which learns domain knowledge from small planning tasks in order to scale up to much larger planning tasks. In this paper, we also highlight and propose the 5 open challenges in the general Learning for Planning field that we believe need to be addressed for advancing the state-of-the-art. |
| title | Graph Learning for Planning: The Story Thus Far and Open Challenges |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.02136 |