AIAug 2, 2021
Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021
arXiv:2108.00633v1
Originality Synthesis-oriented
AI Analysis
This work provides incremental benchmarks for the MaxSAT community to evaluate planning methods using BNNs.
The paper tackles the problem of automated planning with learned binarized neural networks (BNNs) by presenting a MaxSAT encoding and introducing four benchmark domains for evaluation, but it does not report specific results or numbers.
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.