# Planning with Learned Binarized Neural Networks Benchmarks for MaxSAT Evaluation 2021

arXiv: https://arxiv.org/abs/2108.00633 · HTML: https://mlsanity.com/paper/2108.00633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 25 references that are in the map.
- First posted on arXiv 2 Aug 2021.

## Builds on (most cited first, 3 of 3)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Reward Potentials for Planning with Learned Neural Network Transition Models](https://mlsanity.com/paper/1904.09366/) (2019)
- [Encoding Linear Constraints into SAT](https://mlsanity.com/paper/2005.02073/) (2020)

## Abstract (arXiv)

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.