Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021

Say, Buser, Sanner, Scott, Devriendt, Jo, Nordström, Jakob, Stuckey, Peter J.

arXiv.org Artificial Intelligence 

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.