Automatically Learning HTN Methods from Landmarks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914746271268864 |
|---|---|
| author | Li, Ruoxi Nau, Dana Roberts, Mark Fine-Morris, Morgan |
| author_facet | Li, Ruoxi Nau, Dana Roberts, Mark Fine-Morris, Morgan |
| contents | Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce CURRICULAMA, an HTN method learning algorithm that completely automates the learning process. It uses landmark analysis to compose annotated tasks and leverages curriculum learning to order the learning of methods from simpler to more complex. This eliminates the need for manual input, resolving a core issue with HTN-MAKER. We prove CURRICULAMA's soundness, and show experimentally that it has a substantially similar convergence rate in learning a complete set of methods to HTN-MAKER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06325 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automatically Learning HTN Methods from Landmarks Li, Ruoxi Nau, Dana Roberts, Mark Fine-Morris, Morgan Artificial Intelligence Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce CURRICULAMA, an HTN method learning algorithm that completely automates the learning process. It uses landmark analysis to compose annotated tasks and leverages curriculum learning to order the learning of methods from simpler to more complex. This eliminates the need for manual input, resolving a core issue with HTN-MAKER. We prove CURRICULAMA's soundness, and show experimentally that it has a substantially similar convergence rate in learning a complete set of methods to HTN-MAKER. |
| title | Automatically Learning HTN Methods from Landmarks |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06325 |