pyRLprob is a Python library for easy training, evaluation, and postprocessing of OpenAI-Gym environments through Ray-RLlib Reinforcement Learning library.

Use the package manager pip to install the latest stable release of pyRLprob, with all its dependencies:

pip install pyrlprob

To test if the package is installed correctly, run the following tests (one-dimensional landing problem):

import pyrlprob
from pyrlprob.tests import test_train, test_train_eval

test_train()
test_train_eval()

If the code exits without errors, a folder named results/ with the test results will be created in your current directory.

pyRLprob has been created by Lorenzo Federici in 2021. For any problem, clarification or suggestion, you can contact the author at [email protected].

The package is under the MIT license.