Learning Domain-Independent Heuristics for Grounded and Lifted Planning
Dillon Z. Chen, Sylvie Thiébaux, Felipe Trevizan
Abstract
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.
BibTeX
@article{Chen_Thiébaux_Trevizan_2024, title={Learning Domain-Independent Heuristics for Grounded and Lifted Planning}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29986}, DOI={10.1609/aaai.v38i18.29986}, abstractNote={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.}, number={18}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chen, Dillon Z. and Thiébaux, Sylvie and Trevizan, Felipe}, year={2024}, month={Mar.}, pages={20078-20086} }