English

Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021

Artificial Intelligence 2021-08-03 v1

Abstract

This document provides a brief introduction to learned automated planning problem where the state transition function is in the form of a binarized neural network (BNN), presents a general MaxSAT encoding for this problem, and describes the four domains, namely: Navigation, Inventory Control, System Administrator and Cellda, that are submitted as benchmarks for MaxSAT Evaluation 2021.

Cite

@article{arxiv.2108.00633,
  title  = {Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021},
  author = {Buser Say and Scott Sanner and Jo Devriendt and Jakob Nordström and Peter J. Stuckey},
  journal= {arXiv preprint arXiv:2108.00633},
  year   = {2021}
}
R2 v1 2026-06-24T04:44:23.361Z