AI Chat AI Image Generator AI Video Text to Speech

Gym-saturation: an OpenAI Gym environment for saturation provers

03/09/2022

∙

by Boris Shminke, et al.

∙

∙

`gym-saturation` is an OpenAI Gym environment for reinforcement learning (RL) agents capable of proving theorems. Currently, only theorems written in a formal language of the Thousands of Problems for Theorem Provers (TPTP) library in clausal normal form (CNF) are supported. `gym-saturation` implements the 'given clause' algorithm (similar to the one used in Vampire and E Prover). Being written in Python, `gym-saturation` was inspired by PyRes. In contrast to the monolithic architecture of a typical Automated Theorem Prover (ATP), `gym-saturation` gives different agents opportunities to select clauses themselves and train from their experience. Combined with a particular agent, `gym-saturation` can work as an ATP. Even with a non trained agent based on heuristics, `gym-saturation` can find refutations for 688 (of 8257) CNF problems from TPTP v7.5.0.

page 1

page 2

page 3

page 4

research

∙ 04/04/2022

Reinforcement Learning Agents in Colonel Blotto

Models and games are simplified representations of the world. There are ...

0 Joseph Christian G. Noel, et al. ∙

research

∙ 03/05/2021

Training a First-Order Theorem Prover from Synthetic Data

A major challenge in applying machine learning to automated theorem prov...

0 Vlad Firoiu, et al. ∙

research

∙ 09/06/2022

Project proposal: A modular reinforcement learning based automated theorem prover

We propose to build a reinforcement learning prover of independent compo...

0 Boris Shminke, et al. ∙

research

∙ 07/06/2020

INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving

In learning-assisted theorem proving, one of the most critical challenge...

0 Yuhuai Wu, et al. ∙

research

∙ 04/05/2019

HOList: An Environment for Machine Learning of Higher-Order Theorem Proving (extended version)

We present an environment, benchmark, and deep learning driven automated...

2 Kshitij Bansal, et al. ∙

research

∙ 02/13/2023

Universal Agent Mixtures and the Geometry of Intelligence

Inspired by recent progress in multi-agent Reinforcement Learning (RL), ...

0 Samuel Allen Alexander, et al. ∙

research

∙ 09/27/2016

UbuntuWorld 1.0 LTS - A Platform for Automated Problem Solving & Troubleshooting in the Ubuntu OS

In this paper, we present UbuntuWorld 1.0 LTS - a platform for developin...

0 Tathagata Chakraborti, et al. ∙