Learning Domain-Independent Heuristics for Grounded and Lifted Planning

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.

Cite

Text

Chen et al. "Learning Domain-Independent Heuristics for Grounded and Lifted Planning." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I18.29986

Markdown

[Chen et al. "Learning Domain-Independent Heuristics for Grounded and Lifted Planning." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/chen2024aaai-learning-c/) doi:10.1609/AAAI.V38I18.29986

BibTeX

@inproceedings{chen2024aaai-learning-c,
  title     = {{Learning Domain-Independent Heuristics for Grounded and Lifted Planning}},
  author    = {Chen, Dillon Ze and Thiébaux, Sylvie and Trevizan, Felipe W.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {20078-20086},
  doi       = {10.1609/AAAI.V38I18.29986},
  url       = {https://mlanthology.org/aaai/2024/chen2024aaai-learning-c/}
}