GeoDRL: A Self-Learning Framework for Geometry Problem Solving using Reinforcement Learning in Deductive Reasoning

Ensuring both interpretability and correctness is a great challenge in automated geometry problem solving (GPS), and the scarcity of labeled data hinders learning mathematical reasoning from samples. Therefore, we present GeoDRL, a self-learning geometry problem solving framework that integrates logic graph deduction and Deep Reinforcement Learning (DRL) to optimize geometry reasoning as a Markov Decision Process. GeoDRL employs a Graph Neural Network on a Geometry Logic Graph, updating the problem state using a symbolic system. Incorporating DRL into deductive reasoning enables GeoDRL to achieve unsupervised self-learning while maintaining correctness. GeoDRL, through unsupervised learning, exhibits enhanced accuracy in the Geome-try3K dataset, improving by 11.1% over previous SOTA methods, and simultaneously boosts efficiency and interpretability.