RSL-RL: A Learning Library for Robotics Research

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Schwarke, Clemens, Mittal, Mayank, Rudin, Nikita, Hoeller, David, Hutter, Marco
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908537801670656
author Schwarke, Clemens
Mittal, Mayank
Rudin, Nikita
Hoeller, David
Hutter, Marco
author_facet Schwarke, Clemens
Mittal, Mayank
Rudin, Nikita
Hoeller, David
Hutter, Marco
contents RSL-RL is an open-source Reinforcement Learning library tailored to the specific needs of the robotics community. Unlike broad general-purpose frameworks, its design philosophy prioritizes a compact and easily modifiable codebase, allowing researchers to adapt and extend algorithms with minimal overhead. The library focuses on algorithms most widely adopted in robotics, together with auxiliary techniques that address robotics-specific challenges. Optimized for GPU-only training, RSL-RL achieves high-throughput performance in large-scale simulation environments. Its effectiveness has been validated in both simulation benchmarks and in real-world robotic experiments, demonstrating its utility as a lightweight, extensible, and practical framework to develop learning-based robotic controllers. The library is open-sourced at: https://github.com/leggedrobotics/rsl_rl.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RSL-RL: A Learning Library for Robotics Research
Schwarke, Clemens
Mittal, Mayank
Rudin, Nikita
Hoeller, David
Hutter, Marco
Robotics
Machine Learning
RSL-RL is an open-source Reinforcement Learning library tailored to the specific needs of the robotics community. Unlike broad general-purpose frameworks, its design philosophy prioritizes a compact and easily modifiable codebase, allowing researchers to adapt and extend algorithms with minimal overhead. The library focuses on algorithms most widely adopted in robotics, together with auxiliary techniques that address robotics-specific challenges. Optimized for GPU-only training, RSL-RL achieves high-throughput performance in large-scale simulation environments. Its effectiveness has been validated in both simulation benchmarks and in real-world robotic experiments, demonstrating its utility as a lightweight, extensible, and practical framework to develop learning-based robotic controllers. The library is open-sourced at: https://github.com/leggedrobotics/rsl_rl.
title RSL-RL: A Learning Library for Robotics Research
topic Robotics
Machine Learning
url https://arxiv.org/abs/2509.10771