rlberry 0.3.0

A Reinforcement Learning Library for Research and Education

Try it on Google Colab!

What is rlberry?

Writing reinforcement learning algorithms is fun! But after the fun, we have lots of boring things to implement: run our agents in parallel, average and plot results, optimize hyperparameters, compare to baselines, create tricky environments etc etc!

rlberry is a Python library that makes your life easier by doing all these things with a few lines of code, so that you can spend most of your time developing agents. rlberry also provides implementations of several RL agents, benchmark environments and many other useful tools.

Installation

Install the latest version for a stable release.

pip install -U git+https://github.com/rlberry-py/rlberry.git@v0.3.0#egg=rlberry[default]

The documentation includes more installation instructions in particular for users that work with Jax.

Getting started

In our documentation, you will find quick starts to the library and a user guide with a few tutorials on using rlberry.

Also, we provide a handful of notebooks on Google colab as examples to show you how to use rlberry:

Content	Description	Link
Introduction to rlberry	How to create an agent, optimize its hyperparameters and compare to a baseline.
Evaluating and optimizing agents	Train a REINFORCE agent and optimize its hyperparameters

Changelog

See the changelog for a history of the chages made to rlberry.

Citing rlberry

If you use rlberry in scientific publications, we would appreciate citations using the following Bibtex entry:

@misc{rlberry,
    author = {Domingues, Omar Darwiche and Flet-Berliac, Yannis and Leurent, Edouard and M{\'e}nard, Pierre and Shang, Xuedong and Valko, Michal},
    doi = {10.5281/zenodo.5544540},
    month = {10},
    title = {{rlberry - A Reinforcement Learning Library for Research and Education}},
    url = {https://github.com/rlberry-py/rlberry},
    year = {2021}
}

Development notes

The modules listed below are experimental at the moment, that is, they are not thoroughly tested and are susceptible to evolve.

• rlberry.network: Allows communication between a server and client via sockets, and can be used to run agents remotely.

• rlberry.agents.torch, rlberry.agents.jax, rlberry.exploration_tools.torch: Deep RL agents are currently not stable, and their main purpose now is to illustrate how to implement and run those algorithms with the rlberry interface (e.g., run several agents in parallel, optimize hyperparameters etc.). Other libraries, such as Stable Baselines provide reliable implementations of deep RL algorithms, and can be used with rlberry, as shown by this example.

Contributing

Want to contribute to rlberry? Please check our contribution guidelines. If you want to add any new agents or environments, do not hesitate to open an issue!