Automatically Learning HTN Methods from Landmarks

• Published in: Proceedings of the ... International Florida Artificial Intelligence Research Society Conference Vol. 37
• Main Authors: Ruoxi Li, Dana Nau, Mark Roberts, Morgan Fine-Morris
• Format: Journal Article
• Language: English
• Published: LibraryPress@UF 12.05.2024
• ISSN: 2334-0754; 2334-0762; 2334-0762
• DOI: 10.32473/flairs.37.1.135625

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.