6353141
doi
10.5281/zenodo.6353141
oai:zenodo.org:6353141
user-rleap
Blai Bonet
Universitat Pompeu Fabra
Hector Geffner
Universitat Pompeu Fabra
Code and Data for the ICAPS 2022 paper "Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits"
Simon Ståhlberg
Linköping University
info:eu-repo/semantics/openAccess
GNU Affero General Public License v3.0 or later
https://www.gnu.org/licenses/agpl.txt
classical planning
automated planning
machine learning
neural networks
graph neural networks
deep learning
general optimal policies
<p>This archive contains three files:</p>
<ul>
<li>file 'code.zip' contains the code used to train the models;</li>
<li>file 'data.zip' contains the datasets used to train and validate models, and formulas used to test if features are learned by trained models;</li>
<li>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.</li>
</ul>
<p> </p>
Zenodo
2022-03-14
info:eu-repo/semantics/other
6353140
user-rleap
1647420062.850369
24664
md5:9e087d4822de770e9698145775072ec0
https://zenodo.org/records/6353141/files/code.zip
21530876
md5:2bd0098f9c2f2bab36526372bbd13fa2
https://zenodo.org/records/6353141/files/data.zip
21917219
md5:578ad49d9271c5d47ea7cc98cfe12dc1
https://zenodo.org/records/6353141/files/models.zip
public
10.5281/zenodo.6353140
isVersionOf
doi