Reinforcement Learning of Theorem Proving
This addresses the challenge of automated theorem proving for mathematicians and AI researchers, representing a significant advance rather than an incremental improvement.
The researchers tackled automated theorem proving by developing a reinforcement learning approach that uses Monte-Carlo simulations instead of domain heuristics, achieving over 40% more solved problems than a baseline prover on unseen mathematical problems.
We introduce a theorem proving algorithm that uses practically no domain heuristics for guiding its connection-style proof search. Instead, it runs many Monte-Carlo simulations guided by reinforcement learning from previous proof attempts. We produce several versions of the prover, parameterized by different learning and guiding algorithms. The strongest version of the system is trained on a large corpus of mathematical problems and evaluated on previously unseen problems. The trained system solves within the same number of inferences over 40% more problems than a baseline prover, which is an unusually high improvement in this hard AI domain. To our knowledge this is the first time reinforcement learning has been convincingly applied to solving general mathematical problems on a large scale.