Curiosity-driven RL for symbolic equation solving

Kevin O'Keeffe

Keywords: symbolic mathematics, reinforcement learning, curiosity-based exlpo

TL;DR: Curiosity-driven RL + actions based on expression trees solves nonlinear symbolic equation involving radicals, exponentials, and trig functions.

Abstract: We explore if RL can be useful for symbolic mathematics. Previous work showed contrastive learning can solve linear equations in one variable. We show model-free PPO \cite{schulman2017proximal} augmented with curiosity-based exploration and graph-based actions can solve nonlinear equations such as those involving radicals, exponentials, and trig functions. Our work suggests curiosity-based exploration may be useful for general symbolic reasoning tasks.

Submission Number: 21