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.