Symbolic Equation Solving via Reinforcement Learning
arXiv:2401.13447 · doi:10.1016/j.neucom.2024.128732
Abstract
Machine-learning methods are gradually being adopted in a wide variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, which includes tasks like simplifying mathematical terms, calculating formal derivatives, or finding exact solutions of algebraic equations. Traditional software packages for these purposes are commonly based on a huge database of rules for how a specific operation (e.g., differentiation) transforms a certain term (e.g., sine function) into another one (e.g., cosine function). These rules have usually needed to be discovered and subsequently programmed by humans. Efforts to automate this process by machine-learning approaches are faced with challenges like the singular nature of solutions to mathematical problems, when approximations are unacceptable, as well as hallucination effects leading to flawed reasoning. We propose a novel deep-learning interface involving a reinforcement-learning agent that operates a symbolic stack calculator to explore mathematical relations. By construction, this system is capable of exact transformations and immune to hallucination. Using the paradigmatic example of solving linear equations in symbolic form, we demonstrate how our reinforcement-learning agent autonomously discovers elementary transformation rules and step-by-step solutions.
15 pages, 5 figures + appendices 21 pages, 2 figures, 16 tables
References in corpus (14)
- Survey of Hallucination in Natural Language Generation
- A Brief Survey of Deep Reinforcement Learning
- LLaMA: Open and Efficient Foundation Language Models
- PaLM: Scaling Language Modeling with Pathways
- Solving high-dimensional partial differential equations using deep learning
- Sparks of Artificial General Intelligence: Early experiments with GPT-4
- Learning Quadrupedal Locomotion over Challenging Terrain
- LaMDA: Language Models for Dialog Applications
- Solving Quantitative Reasoning Problems with Language Models
- A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
- Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
- Deep Reinforcement Learning and the Deadly Triad
- Deep Symbolic Regression for Recurrent Sequences
- The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)