BriefGPT.xyz
May, 2018
强化学习定理证明
Reinforcement Learning of Theorem Proving
HTML
PDF
Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Mirek Olšák
TL;DR
提出了一种定理证明算法，该算法使用几乎没有领域启发式来指导其连接风格的证明搜索，而是运行许多蒙特卡罗模拟，通过强化学习来指导以前的证明尝试。
Abstract
We introduce a
theorem proving
algorithm that uses practically no domain heuristics for guiding its connection-style proof search. Instead, it runs many
monte-carlo simulations
guided by
→