Learning Domain-Independent Heuristics for Grounded and Lifted Planning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909367191732224 |
|---|---|
| author | Chen, Dillon Z. Thiébaux, Sylvie Trevizan, Felipe |
| author_facet | Chen, Dillon Z. Thiébaux, Sylvie Trevizan, Felipe |
| contents | We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_11143 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Domain-Independent Heuristics for Grounded and Lifted Planning Chen, Dillon Z. Thiébaux, Sylvie Trevizan, Felipe Artificial Intelligence We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics. |
| title | Learning Domain-Independent Heuristics for Grounded and Lifted Planning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2312.11143 |