Adversarial Learning to Reason in an Arbitrary Logic

04/06/2022
by   Stanisław J. Purgał, et al.
0

Existing approaches to learning to prove theorems focus on particular logics and datasets. In this work, we propose Monte-Carlo simulations guided by reinforcement learning that can work in an arbitrarily specified logic, without any human knowledge or set of problems. Since the algorithm does not need any training dataset, it is able to learn to work with any logical foundation, even when there is no body of proofs or even conjectures available. We practically demonstrate the feasibility of the approach in multiple logical systems. The approach is stronger than training on randomly generated data but weaker than the approaches trained on tailored axiom and conjecture sets. It however allows us to apply machine learning to automated theorem proving for many logics, where no such attempts have been tried to date, such as intuitionistic logic or linear logic.

READ FULL TEXT
research
04/15/2019

The ILLTP Library for Intuitionistic Linear Logic

Benchmarking automated theorem proving (ATP) systems using standardized ...
research
03/06/2019

GRUNGE: A Grand Unified ATP Challenge

This paper describes a large set of related theorem proving problems obt...
research
11/10/2017

Judgment aggregation in non-classical logics

This work contributes to the theory of judgment aggregation by discussin...
research
07/25/2002

A Paraconsistent Higher Order Logic

Classical logic predicts that everything (thus nothing useful at all) fo...
research
05/19/2018

Reinforcement Learning of Theorem Proving

We introduce a theorem proving algorithm that uses practically no domain...
research
06/19/2020

Learning to Prove from Synthetic Theorems

A major challenge in applying machine learning to automated theorem prov...
research
11/15/2019

Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling

Recent advances in the integration of deep learning with automated theor...

Please sign up or login with your details

Forgot password? Click here to reset