Code and Data for the KR 2022 paper "Learning Generalized Policies Without Supervision Using GNNs"

This archive contains six files: file 'data.zip' contains the datasets used to train and validate models; file 'derived_predicate.zip' contains code for augmenting datasets with derived predicates; file 'generators.zip' contains the custom generators we used, in this case, spanner-bidirectional; file 'models.zip' contains the trained models we used in the experiments; file 'network.zip' contains the code for training and validating models; file 'results.zip' contains executions of the trained models on the test set, and code for generating the LaTeX table.

Related Organizations

Linköping University
Sweden
Universitat Pompeu Fabra
Spain

Keywords

automated planning, machine learning, graph neural networks, deep learning, general policies, neural networks, classical planning

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average