gym-saturation 0.1.5

An OpenAI Gym environment for saturation provers

gym-saturation

gym-saturation is an OpenAI Gym environment for reinforcement learning (RL) agents capable of proving theorems. Currently, only theorems in CNF sublanguage of TPTP are supported. gym-saturation implements the 'given clause' algorithm (similar to one used in Vampire and E Prover). Although, being written in Python, gym-saturation is closer to PyRes. In contrast to monolithic architecture of a typical 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 Automated Theorem Prover (ATP).

gym-saturation can be interesting for RL practitioners willing to apply their experience to theorem proving without coding all the logic-related stuff themselves. It also can be useful for automated deduction researchers who want to create an RL-empowered ATP.

How to Install

The best way to install this package is to use pip:

pip install gym-saturation

One also can run it in a Docker container:

docker build -t gym-saturation https://github.com/inpefess/gym-saturation.git
docker run -it --rm -p 8888:8888 gym-saturation jupyter-lab --ip=0.0.0.0 --port=8888 --no-browser

How to use

See the notebook or run it in Binder for more information.

How to Contribute

Pull requests are welcome. To start:

git clone https://github.com/inpefess/gym-saturation
cd gym-saturation
# activate python virtual environment with Python 3.6+
pip install -U pip
pip install -U setuptools wheel poetry
poetry install
# recommended but not necessary
pre-commit install

To check the code quality before creating a pull request, one might run the script show_report.sh. It locally does nearly the same as the CI pipeline after the PR is created.

Reporting issues or problems with the software

Questions and bug reports are welcome on the tracker.

More documentation

More documentation can be found here.