BriefGPT.xyz
Jul, 2018
通过深度强化学习学习量化布尔公式的启发式
Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning
HTML
PDF
Gil Lederman, Markus N. Rabe, Sanjit A. Seshia
TL;DR
本文介绍了一种基于深度强化学习的高效启发式算法来自动推理量化Boolean公式。针对回溯搜索算法，在一类具有挑战性的问题集上，该算法能够解决比现有手写算法更多的公式。
Abstract
We demonstrate how to learn efficient
heuristics
for
automated reasoning
algorithms through
deep reinforcement learning
. We consider searc
→