Learning Heuristics for Quantified Boolean Formulas Through Reinforcement Learning
Abstract
We demonstrate how to learn efficient heuristics for automated reasoning algorithms for quantified Boolean formulas through deep reinforcement learning. We focus on a backtracking search algorithm, which can already solve formulas of impressive size - up to hundreds of thousands of variables. The main challenge is to find a representation of these formulas that lends itself to making predictions in a scalable way. For a family of challenging problems, we learned a heuristic that solves significantly more formulas compared to the existing handwritten heuristics.
Cite
Text
Lederman et al. "Learning Heuristics for Quantified Boolean Formulas Through Reinforcement Learning." International Conference on Learning Representations, 2020.Markdown
[Lederman et al. "Learning Heuristics for Quantified Boolean Formulas Through Reinforcement Learning." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/lederman2020iclr-learning/)BibTeX
@inproceedings{lederman2020iclr-learning,
title = {{Learning Heuristics for Quantified Boolean Formulas Through Reinforcement Learning}},
author = {Lederman, Gil and Rabe, Markus and Seshia, Sanjit and Lee, Edward A.},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/lederman2020iclr-learning/}
}