Curiosity-driven RL for symbolic equation solving
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _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 |