/prl

Open-source library for a reinforcement learning research.

Primary LanguagePythonMIT LicenseMIT

People's Reinforcement Learning (PRL)

DOI

Description

This is a reinforcement learning framework made with research activity in mind. You can read mode about PRL in our introductory blog post, in-depth look into library, documentation or wiki.

System requirements

  • python 3.6
  • swig
  • python3-dev

We recommend using virtualenv for installing project dependencies.

Installation

  • clone the project:

    git clone git@gitlab.com:opium-sh/prl.git

  • create and activate a virtualenv for the project (you can skip this step if you are not using virtualenv)

    virtualenv -p python3.6 your/path && source your/path/bin/activate

  • install dependencies:

    pip install -r requirements.txt

  • install library

    pip install -e .

  • run example:

    cd examples
python cart_pole_example_cross_entropy.py

Citation

If you use PRL in your work or research please cite us as:

Tempczyk, P., Sliwowski, M., Kozakowski, P., Smuda, P., Topolski, B., Nabrdalik, F., & Malisz, T. (2020). opium-sh/prl: First release of Peoples’s Reinforcement Learning (PRL). Zenodo. https://doi.org/10.5281/ZENODO.3662113