gym-saturation: Gymnasium environments for saturation provers (System description)
This work provides tools for researchers in automated theorem proving to experiment with reinforcement learning, but it is incremental as it builds on a previously published package.
The authors updated gym-saturation, a Python package providing Gymnasium environments for guiding saturation-style theorem provers with reinforcement learning, demonstrating usage with Vampire and iProver provers and applying Thompson sampling and Proximal Policy Optimization algorithms via Ray RLlib.
This work describes a new version of a previously published Python package - gym-saturation: a collection of OpenAI Gym environments for guiding saturation-style provers based on the given clause algorithm with reinforcement learning. We contribute usage examples with two different provers: Vampire and iProver. We also have decoupled the proof state representation from reinforcement learning per se and provided examples of using a known ast2vec Python code embedding model as a first-order logic representation. In addition, we demonstrate how environment wrappers can transform a prover into a problem similar to a multi-armed bandit. We applied two reinforcement learning algorithms (Thompson sampling and Proximal policy optimisation) implemented in Ray RLlib to show the ease of experimentation with the new release of our package.