RSL-RL Documentation

RSL-RL is a GPU-accelerated, lightweight learning library for robotics research. Its compact design allows researchers to prototype and test new ideas without the overhead of modifying large, complex libraries. RSL-RL supports multi-GPU training and features common algorithms for robot learning. The core library, without the additional features of this branch, is also available via PyPI.

Additional Features

This is the documentation for the extras branch of RSL-RL, which contains additional features that are not part of the core library. These features, mostly contributed by the community, are listed below and described in the overview.

  • No additional features yet :(

Learning Environments

RSL-RL is currently used by the following robot learning libraries:

Citation

If you use RSL-RL in your research, please cite the paper:

@article{schwarke2025rslrl,
  title={RSL-RL: A Learning Library for Robotics Research},
  author={Schwarke, Clemens and Mittal, Mayank and Rudin, Nikita and Hoeller, David and Hutter, Marco},
  journal={arXiv preprint arXiv:2509.10771},
  year={2025}
}