HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving
Kshitij Bansal, Sarah Loos, Markus Rabe, Christian Szegedy, Stewart Wilcox
Abstract
We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an interesting challenge for deep learning. We provide an open-source framework based on the HOL Light theorem prover that can be used as a reinforcement learning environment. HOL Light comes with a broad coverage of basic mathematical theorems on calculus and the formal proof of the Kepler conjecture, from which we derive a challenging benchmark for automated reasoning approaches. We also present a deep reinforcement learning driven automated theorem prover, DeepHOL, that gives strong initial results on this benchmark.
BibTeX
@InProceedings{pmlr-v97-bansal19a,
title = {{HOL}ist: An Environment for Machine Learning of Higher Order Logic Theorem Proving},
author = {Bansal, Kshitij and Loos, Sarah and Rabe, Markus and Szegedy, Christian and Wilcox, Stewart},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {454--463},
year = {2019},
editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume = {97},
series = {Proceedings of Machine Learning Research},
month = {09--15 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v97/bansal19a/bansal19a.pdf},
url = {https://proceedings.mlr.press/v97/bansal19a.html},
abstract = {We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an interesting challenge for deep learning. We provide an open-source framework based on the HOL Light theorem prover that can be used as a reinforcement learning environment. HOL Light comes with a broad coverage of basic mathematical theorems on calculus and the formal proof of the Kepler conjecture, from which we derive a challenging benchmark for automated reasoning approaches. We also present a deep reinforcement learning driven automated theorem prover, DeepHOL, that gives strong initial results on this benchmark.}
}