arXiv:2510.17022cs.LGcs.AI2025-10中稿 · NeurIPS
用好奇心驱动强化学习解非线性符号方程
Curiosity-driven RL for symbolic equation solving
- 基于好奇心探索与图结构动作的PPO算法
- 成功求解含根号、指数、三角函数的方程
- 适合对符号推理感兴趣的AI研究者
我们探索强化学习在符号数学中的应用价值。已有工作表明对比学习可求解一元线性方程。本文展示，采用好奇心驱动探索并结合图结构动作的无模型PPO算法，能够求解包含根号、指数和三角函数的非线性方程。结果表明，好奇心驱动探索可能适用于更广泛的符号推理任务。
原文摘要 · Abstract (English)
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.
强化学习符号推理方程求解
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。