Software Open Access

Code and Data for the ICAPS 2022 paper "Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits"

Simon Ståhlberg; Blai Bonet; Hector Geffner

This archive contains three files:

  • file 'code.zip' contains the code used to train the models;
  • file 'data.zip' contains the datasets used to train and validate models, and formulas used to test if features are learned by trained models;
  • file 'models.zip' contains the final trained models together with logs from both training and evaluation, and the linear transformation between learned and hand-crafted features.

 

Files (43.5 MB)
Name Size
code.zip
md5:9e087d4822de770e9698145775072ec0
24.7 kB Download
data.zip
md5:2bd0098f9c2f2bab36526372bbd13fa2
21.5 MB Download
models.zip
md5:578ad49d9271c5d47ea7cc98cfe12dc1
21.9 MB Download
98
62
views
downloads
All versions This version
Views 9898
Downloads 6262
Data volume 846.8 MB846.8 MB
Unique views 8181
Unique downloads 3131

Share

Cite as