Salvato in:
Dettagli Bibliografici
Autore principale: O'Keeffe, Kevin P.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.17022
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915584577372160
author O'Keeffe, Kevin P.
author_facet O'Keeffe, Kevin P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17022
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Curiosity-driven RL for symbolic equation solving
O'Keeffe, Kevin P.
Machine Learning
Artificial Intelligence
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.
title Curiosity-driven RL for symbolic equation solving
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.17022