Published August 9, 2024 | Version v1
Software Open

Code and Data for the Paper titled "Symmetries and Expressive Requirements for Learning General Policies"

  • 1. ROR icon Linköping University
  • 2. Universitat Pompeu Fabra
  • 3. Instituciò Catalana de Recerca i Estudis Avancats

Description

The files code-learning_general_policies-without_symmetry_reduction.zip and data-learning_general_policies-without_symmetry_reduction.zip contain the code and data, respectively, from Table 2 of the paper on learning general policies on a collection of classical planning benchmarks without symmetry reduction.

The files code-learning_general_policies-with_symmetry_reduction.zip and data-learning_general_policies-with_symmetry_reduction.zip contain the code and data, respectively, from Table 2 of the paper on learning general policies on a collection of classical planning benchmarks with symmetry reduction. A GitHub repository is available here.

The files code-weisfeiler_leman_expressivity.zip and data-weisfeiler_leman_expressivity.zip contain the code and data, respectively, from Table 1 of the paper on finding expressivity conflicts using the Weisfeiler-Leman algorithm on a collection of classical planning benchmarks. A GitHub repository is available here.

Additional Acknowledgements: This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.

Files

code-learning_general_policies-with_symmetry_reduction.zip

Additional details

Funding

European Commission
RLeap - From Data-based to Model-based AI: Representation Learning for Planning 885107
European Commission
TAILOR - Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization 952215