paper

Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021

arXiv:2108.00633

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.

References in corpus (1)

Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021 · wovepaper