RSL-RL
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 can also be used out-of-the-box by installing it via PyPI, supports multi-GPU training, and features common algorithms for robot learning.
Additional algorithms, models, and more, mainly contributed by the community, can be found on the
extrasbranch. This allows us to keep the core library onmainminimal and easy to start with. To see a list of the additional features, please check the Extras Documentation.
Key Features
- Minimal, readable codebase with clear extension points for rapid prototyping.
- Robotics-first methods including PPO and Student-Teacher Distillation.
- High-throughput training with native Multi-GPU support.
- Proven performance in numerous research publications.
Learning Environments
RSL-RL is currently used by the following robot learning libraries:
- Isaac Lab (built on top of NVIDIA Isaac Sim)
- Legged Gym (built on top of NVIDIA Isaac Gym)
- mjlab (built on top of MuJoCo Warp)
- MuJoCo Playground (built on top of MuJoCo MJX and Warp)
Installation
Before installing RSL-RL, ensure that Python 3.9+ is available. It is recommended to install the library in a virtual
environment (e.g. using venv or conda), which is often already created by the used environment library (e.g.
Isaac Lab). If so, make sure to activate it before installing RSL-RL.
Installing RSL-RL as a dependency
pip install rsl-rl-lib
Installing RSL-RL for development
git clone https://github.com/leggedrobotics/rsl_rl
cd rsl_rl
pip install -e .
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}
}
Metadata
Release files for rsl-rl-lib 5.5.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| rsl_rl_lib-5.5.2.tar.gz | 68.9 kB | Without provenance | Details for rsl_rl_lib-5.5.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| rsl_rl_lib-5.5.2-py3-none-any.whl | Python 3 | none | any | Details for rsl_rl_lib-5.5.2-py3-none-any.whl |
Total release size: 169.6 kB
Release files / rsl_rl_lib-5.5.2.tar.gz
| Download URL | rsl_rl_lib-5.5.2.tar.gz |
|---|---|
| Size | 68.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5bafde369a794e46378d65a2b67a0887da91189ba8c398419e5d0de76b13f3ff
|
|
BLAKE2b-256 checksum How to use checksums |
29ce44a29895a6df8b91f88ad366ba7928e1af61364297a4ea9886c0bb1dd303
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.23
|
Release files / rsl_rl_lib-5.5.2-py3-none-any.whl
| Download URL | rsl_rl_lib-5.5.2-py3-none-any.whl |
|---|---|
| Size | 100.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
559a7707cfe6233b359ff79e28eaddd4751d8350bd9a0bc62f36c1507f44e7d8
|
|
BLAKE2b-256 checksum How to use checksums |
425b7381036e2b6413989341b7301690cf973111816dde9e181fa1af37152315
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.23
|
Security for rsl-rl-lib 5.5.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.