Published March 24, 2022 | Version v1
Software Open

Proofs, Code, and Data for the ICAPS 2022 Paper

  • 1. Linköping University
  • 2. ICREA, Universitat Pompeu Fabra, Linköping University


This upload contains code and data for learning policy sketches for classical planning domains and comparing the planners (1) first iteration of LAMA, (2) Dual-BFWS, (3) Serialized Iterated Width (SIW), and (4) Serialized Iterated Width with Sketches (SIWR) on a subset of classical planning benchmarks. The upload also contains an extended version of the paper published at ICAPS with further details and proofs.

- contains a subset of classical planning domains.

- contains experimental code and data for learning sketches and testing the four planners from above

- contains textual representation of sketches for some of these domains, which can be given as input to the SIWR planner, and the logs generated when learning policy sketches.

- drexler-et-al-icaps2022-extended.pdf is an extended version of the paper published at the 32nd International Conference on Automated Planning and Scheduling (ICAPS2022).


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. - The computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973


Files (927.0 MB)

Name Size Download all
6.1 MB Preview Download
919.8 MB Preview Download
779.2 kB Preview Download
309.3 kB Preview Download

Additional details

Related works

Software: 10.5281/zenodo.6343567 (DOI)


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