Papers › Project proposal: A modular reinforcement learning based automated theorem prover

Project proposal: A modular reinforcement learning based automated theorem prover

6 Sep 2022arXiv:2209.02562archive 2025-07-28

Boris Shminke

We propose to build a reinforcement learning prover of independent components: a deductive system (an environment), the proof state representation (how an agent sees the environment), and an agent training algorithm. To that purpose, we contribute an additional Vampire-based environment to gym-saturation package of OpenAI Gym environments for saturation provers. We demonstrate a prototype of using gym-saturation together with a popular reinforcement learning framework (Ray RLlib). Finally, we discuss our plans for completing this work in progress to a competitive automated theorem prover.

PaperPDFCode

Code

inpefess/basic-rl-prover officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

OpenAI GymReinforcement LearningReinforcement Learning (RL)reinforcement-learningrllib

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections