Welcome to metarl¶
metarl is a framework for developing and evaluating reinforcement learning algorithms.
metarl is a work in progress, input is welcome. The available documentation is limited for now.
User Guide¶
The metarl user guide explains how to install metarl, how to run experiments, and how to implement new MDPs and new algorithms.
Citing metarl¶
If you use metarl for academic research, please cite the repository using the following BibTeX entry. You should update the commit field with the commit or release tag your publication uses.
@misc{metarl,
author = {The metarl contributors},
title = {MetaRL: A toolkit for reproducible reinforcement learning research},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/rlworkgroup/metarl}},
commit = {ebd7800430b0212c3ffcf78fd3ec26b22097c371}
}